{ "book_title": "Hands on Machine Learning with Scikit Learn and TensorFlow", "days": [ { "day": 1, "title": "Day 1", "topics": [ { "name": "What Is Machine Learning?", "chapter": "The Fundamentals of Machine Learning", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Why Use Machine Learning?", "chapter": "The Fundamentals of Machine Learning", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Types of Machine Learning Systems", "chapter": "The Fundamentals of Machine Learning", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Supervised/Unsupervised Learning", "chapter": "The Fundamentals of Machine Learning", "summary": "", "difficulty": "beginner", "prerequisites": [] } ], "goal": "Progress through What Is Machine Learning?, Why Use Machine Learning?, Types of Machine Learning Systems, then wrap with Supervised/Unsupervised Learning.", "estimated_minutes": 180 }, { "day": 2, "title": "Day 2", "topics": [ { "name": "Batch and Online Learning", "chapter": "The Fundamentals of Machine Learning", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Main Challenges of Machine Learning", "chapter": "Instance-Based Versus Model-Based Learning", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Testing and Validating", "chapter": "Stepping Back", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Working with Real Data", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [] } ], "goal": "Progress through Batch and Online Learning, Main Challenges of Machine Learning, Testing and Validating, then wrap with Working with Real Data.", "estimated_minutes": 180 }, { "day": 3, "title": "Day 3", "topics": [ { "name": "Training and Evaluating on the Training Set", "chapter": "Select and Train a Model", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Analyze the Best Models and Their Errors", "chapter": "Select and Train a Model", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Try It Out!", "chapter": "Evaluate Your System on the Test Set", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "MNIST", "chapter": "3. Classification", "summary": "", "difficulty": "beginner", "prerequisites": [] } ], "goal": "Progress through Training and Evaluating on the Training Set, Analyze the Best Models and Their Errors, Try It Out!, then wrap with MNIST.", "estimated_minutes": 180 }, { "day": 4, "title": "Day 4", "topics": [ { "name": "Linear Regression", "chapter": "4. Training Models", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Learning Curves", "chapter": "Mini-batch Gradient Descent", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Early Stopping", "chapter": "Mini-batch Gradient Descent", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Logistic Regression", "chapter": "Logistic Regression", "summary": "", "difficulty": "intermediate", "prerequisites": [] } ], "goal": "Progress through Linear Regression, Learning Curves, Early Stopping, then wrap with Logistic Regression.", "estimated_minutes": 196 }, { "day": 5, "title": "Day 5", "topics": [ { "name": "Linear SVM Classification", "chapter": "Support Vector Machines", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Training and Visualizing a Decision Tree", "chapter": "Decision Trees", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Making Predictions", "chapter": "Decision Trees", "summary": "", "difficulty": "beginner", "prerequisites": [ "Decision Trees" ] }, { "name": "Estimating Class Probabilities", "chapter": "Decision Trees", "summary": "", "difficulty": "beginner", "prerequisites": [ "Decision Trees" ] } ], "goal": "Progress through Linear SVM Classification, Training and Visualizing a Decision Tree, Making Predictions, then wrap with Estimating Class Probabilities.", "estimated_minutes": 196 }, { "day": 6, "title": "Day 6", "topics": [ { "name": "Regression", "chapter": "Regression", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "The Curse of Dimensionality", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Other Dimensionality Reduction Techniques", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "advanced", "prerequisites": [ "Dimensionality Reduction" ] }, { "name": "Up and Running with TensorFlow", "chapter": "Neural Networks and Deep Learning", "summary": "", "difficulty": "beginner", "prerequisites": [] } ], "goal": "Progress through Regression, The Curse of Dimensionality, Other Dimensionality Reduction Techniques, then wrap with Up and Running with TensorFlow.", "estimated_minutes": 212 }, { "day": 7, "title": "Day 7", "topics": [ { "name": "Name Scopes", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "From Biological to Artificial Neurons", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Vanishing/Exploding Gradients Problems", "chapter": "Training Deep Neural Nets", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Reusing a TensorFlow Model", "chapter": "Reusing and Tweaking Models", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Training a TensorFlow Model" ] } ], "goal": "Progress through Name Scopes, From Biological to Artificial Neurons, Vanishing/Exploding Gradients Problems, then wrap with Reusing a TensorFlow Model.", "estimated_minutes": 196 }, { "day": 8, "title": "Day 8", "topics": [ { "name": "Reusing Models from Other Frameworks", "chapter": "Reusing and Tweaking Models", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Training a Model in Another Framework" ] }, { "name": "Freezing the Lower Layers", "chapter": "Reusing and Tweaking Models", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Training a Neural Network" ] }, { "name": "Tweaking, Dropping, or Replacing the Upper Layers", "chapter": "Reusing and Tweaking Models", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Training a Neural Network" ] }, { "name": "Model Zoos", "chapter": "Reusing and Tweaking Models", "summary": "", "difficulty": "beginner", "prerequisites": [] } ], "goal": "Progress through Reusing Models from Other Frameworks, Freezing the Lower Layers, Tweaking, Dropping, or Replacing the Upper Layers, then wrap with Model Zoos.", "estimated_minutes": 227 }, { "day": 9, "title": "Day 9", "topics": [ { "name": "Unsupervised Pretraining", "chapter": "Reusing and Tweaking Models", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Pretraining on an Auxiliary Task", "chapter": "Reusing and Tweaking Models", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Faster Optimizers", "chapter": "Optimizers and Regularization", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Momentum Optimization", "chapter": "Optimizers and Regularization", "summary": "", "difficulty": "intermediate", "prerequisites": [] } ], "goal": "Progress through Unsupervised Pretraining, Pretraining on an Auxiliary Task, Faster Optimizers, then wrap with Momentum Optimization.", "estimated_minutes": 243 }, { "day": 10, "title": "Day 10", "topics": [ { "name": "Nesterov Accelerated Gradient", "chapter": "Optimizers and Regularization", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "AdaGrad", "chapter": "Optimizers and Regularization", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "RMSProp", "chapter": "Optimizers and Regularization", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Adam Optimization", "chapter": "Optimizers and Regularization", "summary": "", "difficulty": "intermediate", "prerequisites": [] } ], "goal": "Progress through Nesterov Accelerated Gradient, AdaGrad, RMSProp, then wrap with Adam Optimization.", "estimated_minutes": 243 }, { "day": 11, "title": "Day 11", "topics": [ { "name": "Learning Rate Scheduling", "chapter": "Optimizers and Regularization", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Avoiding Overfitting Through Regularization", "chapter": "Optimizers and Regularization", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "\u21131 and \u21132 Regularization", "chapter": "Early Stopping and Regularization Techniques", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Dropout", "chapter": "Early Stopping and Regularization Techniques", "summary": "", "difficulty": "intermediate", "prerequisites": [] } ], "goal": "Progress through Learning Rate Scheduling, Avoiding Overfitting Through Regularization, \u21131 and \u21132 Regularization, then wrap with Dropout.", "estimated_minutes": 243 }, { "day": 12, "title": "Day 12", "topics": [ { "name": "Max-Norm Regularization", "chapter": "Early Stopping and Regularization Techniques", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Multiple Devices on a Single Machine", "chapter": "Distributing TensorFlow Across Devices and Servers", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Managing the GPU RAM", "chapter": "Distributing TensorFlow Across Devices and Servers", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Placing Operations on Devices", "chapter": "Distributing TensorFlow Across Devices and Servers", "summary": "", "difficulty": "intermediate", "prerequisites": [] } ], "goal": "Progress through Max-Norm Regularization, Multiple Devices on a Single Machine, Managing the GPU RAM, then wrap with Placing Operations on Devices.", "estimated_minutes": 243 }, { "day": 13, "title": "Day 13", "topics": [ { "name": "Parallel Execution", "chapter": "Distributing TensorFlow Across Devices and Servers", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Control Dependencies", "chapter": "Distributing TensorFlow Across Devices and Servers", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Multiple Devices Across Multiple Servers", "chapter": "Distributing TensorFlow Across Devices and Servers", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Opening a Session", "chapter": "Distributing TensorFlow Across Devices and Servers", "summary": "", "difficulty": "intermediate", "prerequisites": [] } ], "goal": "Progress through Parallel Execution, Control Dependencies, Multiple Devices Across Multiple Servers, then wrap with Opening a Session.", "estimated_minutes": 243 }, { "day": 14, "title": "Day 14", "topics": [ { "name": "The Master and Worker Services", "chapter": "Distributed Training and Parallel Execution", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Pinning Operations Across Tasks", "chapter": "Distributed Training and Parallel Execution", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Sharding Variables Across Multiple Parameter Servers", "chapter": "Distributed Training and Parallel Execution", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Sharing State Across Sessions Using Resource Containers", "chapter": "Distributed Training and Parallel Execution", "summary": "", "difficulty": "intermediate", "prerequisites": [] } ], "goal": "Progress through The Master and Worker Services, Pinning Operations Across Tasks, Sharding Variables Across Multiple Parameter Servers, then wrap with Sharing State Across Sessions Using Resource Containers.", "estimated_minutes": 243 }, { "day": 15, "title": "Day 15", "topics": [ { "name": "Asynchronous Communication Using TensorFlow Queues", "chapter": "Distributed Training and Parallel Execution", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Loading Data Directly from the Graph", "chapter": "Distributed Training and Parallel Execution", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Parallelizing Neural Networks on a TensorFlow Cluster", "chapter": "Distributed Training and Parallel Execution", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "In-Graph Versus Between-Graph Replication", "chapter": "Distributed Training", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] } ], "goal": "Progress through Asynchronous Communication Using TensorFlow Queues, Loading Data Directly from the Graph, Parallelizing Neural Networks on a TensorFlow Cluster, then wrap with In-Graph Versus Between-Graph Replication.", "estimated_minutes": 243 }, { "day": 16, "title": "Day 16", "topics": [ { "name": "Model Parallelism", "chapter": "Distributed Training", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Data Parallelism", "chapter": "Distributed Training", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "The Architecture of the Visual Cortex", "chapter": "Convolutional Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Convolutional Layer", "chapter": "Convolutional Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "basic understanding of machine learning" ] } ], "goal": "Progress through Model Parallelism, Data Parallelism, The Architecture of the Visual Cortex, then wrap with Convolutional Layer.", "estimated_minutes": 212 }, { "day": 17, "title": "Day 17", "topics": [ { "name": "Filters", "chapter": "Convolutional Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Stacking Multiple Feature Maps", "chapter": "Convolutional Neural Networks", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "TensorFlow Implementation", "chapter": "Convolutional Neural Networks", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Memory Requirements", "chapter": "Convolutional Neural Networks", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] } ], "goal": "Progress through Filters, Stacking Multiple Feature Maps, TensorFlow Implementation, then wrap with Memory Requirements.", "estimated_minutes": 227 }, { "day": 18, "title": "Day 18", "topics": [ { "name": "Pooling Layer", "chapter": "Convolutional Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "CNN Architectures", "chapter": "Convolutional Neural Networks", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Recurrent Neurons", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Memory Cells", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "basic understanding of machine learning" ] } ], "goal": "Progress through Pooling Layer, CNN Architectures, Recurrent Neurons, then wrap with Memory Cells.", "estimated_minutes": 196 }, { "day": 19, "title": "Day 19", "topics": [ { "name": "Input and Output Sequences", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Basic RNNs in TensorFlow", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Static Unrolling Through Time", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Dynamic Unrolling Through Time", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] } ], "goal": "Progress through Input and Output Sequences, Basic RNNs in TensorFlow, Static Unrolling Through Time, then wrap with Dynamic Unrolling Through Time.", "estimated_minutes": 227 }, { "day": 20, "title": "Day 20", "topics": [ { "name": "Handling Variable Length Input Sequences", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Handling Variable-Length Output Sequences", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Training RNNs", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Training a Sequence Classifier", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] } ], "goal": "Progress through Handling Variable Length Input Sequences, Handling Variable-Length Output Sequences, Training RNNs, then wrap with Training a Sequence Classifier.", "estimated_minutes": 243 }, { "day": 21, "title": "Day 21", "topics": [ { "name": "Training to Predict Time Series", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Creative RNN", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "advanced", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Deep RNNs", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "advanced", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Distributing a Deep RNN Across Multiple GPUs", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "advanced", "prerequisites": [ "basic understanding of machine learning" ] } ], "goal": "Progress through Training to Predict Time Series, Creative RNN, Deep RNNs, then wrap with Distributing a Deep RNN Across Multiple GPUs.", "estimated_minutes": 290 }, { "day": 22, "title": "Day 22", "topics": [ { "name": "Applying Dropout", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "advanced", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "The Difficulty of Training over Many Time Steps", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "advanced", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "LSTM Cell", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Peephole Connections", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "basic understanding of machine learning" ] } ], "goal": "Progress through Applying Dropout, The Difficulty of Training over Many Time Steps, LSTM Cell, then wrap with Peephole Connections.", "estimated_minutes": 243 }, { "day": 23, "title": "Day 23", "topics": [ { "name": "GRU Cell", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Natural Language Processing", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "advanced", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Word Embeddings", "chapter": "Recurrent Neural Networks", "summary": "", "difficulty": "advanced", "prerequisites": [ "basic understanding of machine learning" ] }, { "name": "Encoder-Decoder Networks for Machine Translation", "chapter": "An Encoder\u2013Decoder Network for Machine Translation", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of neural networks" ] } ], "goal": "Progress through GRU Cell, Natural Language Processing, Word Embeddings, then wrap with Encoder-Decoder Networks for Machine Translation.", "estimated_minutes": 259 }, { "day": 24, "title": "Day 24", "topics": [ { "name": "Introduction to Autoencoders", "chapter": "Autoencoders", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of neural networks" ] }, { "name": "Efficient Data Representations", "chapter": "Autoencoders", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of neural networks" ] }, { "name": "Tying Weights", "chapter": "Autoencoders", "summary": "", "difficulty": "advanced", "prerequisites": [ "basic understanding of neural networks" ] }, { "name": "Training One Autoencoder at a Time", "chapter": "Autoencoders", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of neural networks" ] } ], "goal": "Progress through Introduction to Autoencoders, Efficient Data Representations, Tying Weights, then wrap with Training One Autoencoder at a Time.", "estimated_minutes": 259 }, { "day": 25, "title": "Day 25", "topics": [ { "name": "Unsupervised Pretraining Using Stacked Autoencoders", "chapter": "Autoencoders", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of neural networks" ] }, { "name": "Denoising Autoencoders", "chapter": "Autoencoders", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of neural networks" ] }, { "name": "Sparse Autoencoders", "chapter": "Autoencoders", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of neural networks" ] }, { "name": "Introduction to Reinforcement Learning", "chapter": "Reinforcement Learning", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of neural networks" ] } ], "goal": "Progress through Unsupervised Pretraining Using Stacked Autoencoders, Denoising Autoencoders, Sparse Autoencoders, then wrap with Introduction to Reinforcement Learning.", "estimated_minutes": 243 }, { "day": 26, "title": "Day 26", "topics": [ { "name": "Learning to Optimize Rewards", "chapter": "Reinforcement Learning", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of neural networks" ] }, { "name": "Neural Network Policies", "chapter": "Reinforcement Learning", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of neural networks" ] }, { "name": "Evaluating Actions: The Credit Assignment Problem", "chapter": "Reinforcement Learning", "summary": "", "difficulty": "intermediate", "prerequisites": [ "basic understanding of neural networks" ] }, { "name": "The Machine Learning Tsunami", "chapter": "Index", "summary": "", "difficulty": "beginner", "prerequisites": [] } ], "goal": "Progress through Learning to Optimize Rewards, Neural Network Policies, Evaluating Actions: The Credit Assignment Problem, then wrap with The Machine Learning Tsunami.", "estimated_minutes": 227 }, { "day": 27, "title": "Day 27", "topics": [ { "name": "Machine Learning in Your Projects", "chapter": "Index", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Objective and Approach", "chapter": "Index", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Introduction to Machine Learning and Scikit-Learn/TensorFlow", "chapter": "Preface", "summary": "", "difficulty": "beginner", "prerequisites": [ "Python programming experience", "NumPy, Pandas, and Matplotlib" ] }, { "name": "Prerequisites", "chapter": "Preface", "summary": "", "difficulty": "beginner", "prerequisites": [] } ], "goal": "Progress through Machine Learning in Your Projects, Objective and Approach, Introduction to Machine Learning and Scikit-Learn/TensorFlow, then wrap with Prerequisites.", "estimated_minutes": 180 }, { "day": 28, "title": "Day 28", "topics": [ { "name": "The Fundamentals of Machine Learning", "chapter": "Roadmap", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Part I: The Fundamentals of Machine Learning" ] }, { "name": "Neural Networks and Deep Learning", "chapter": "Roadmap", "summary": "", "difficulty": "advanced", "prerequisites": [ "Part I: The Fundamentals of Machine Learning" ] }, { "name": "Introduction to Machine Learning", "chapter": "Other Resources", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Recommended Books", "chapter": "Other Resources", "summary": "", "difficulty": "beginner", "prerequisites": [] } ], "goal": "Progress through The Fundamentals of Machine Learning, Neural Networks and Deep Learning, Introduction to Machine Learning, then wrap with Recommended Books.", "estimated_minutes": 227 }, { "day": 29, "title": "Day 29", "topics": [ { "name": "Conventions Used in This Book", "chapter": "Other Resources", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Using Code Examples", "chapter": "Other Resources", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Contact Information", "chapter": "How to Contact Us", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Author's Acknowledgments", "chapter": "Acknowledgments", "summary": "", "difficulty": "beginner", "prerequisites": [] } ], "goal": "Progress through Conventions Used in This Book, Using Code Examples, Contact Information, then wrap with Author's Acknowledgments.", "estimated_minutes": 180 }, { "day": 30, "title": "Day 30", "topics": [ { "name": "Traditional Approach vs. Machine Learning", "chapter": "Why Use Machine Learning?", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Attributes and Features", "chapter": "Machine Learning Landscape", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Clustering", "chapter": "Unsupervised Learning", "summary": "", "difficulty": "beginner", "prerequisites": [ "Unsupervised Learning" ] }, { "name": "Visualization and Dimensionality Reduction", "chapter": "Unsupervised Learning", "summary": "", "difficulty": "beginner", "prerequisites": [ "Unsupervised Learning" ] } ], "goal": "Progress through Traditional Approach vs. Machine Learning, Attributes and Features, Clustering, then wrap with Visualization and Dimensionality Reduction.", "estimated_minutes": 180 }, { "day": 31, "title": "Day 31", "topics": [ { "name": "Association Rule Learning", "chapter": "Unsupervised Learning", "summary": "", "difficulty": "beginner", "prerequisites": [ "Unsupervised Learning" ] }, { "name": "Semisupervised learning", "chapter": "Semisupervised learning", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Batch learning", "chapter": "Batch and Online Learning", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Online learning", "chapter": "Batch and Online Learning", "summary": "", "difficulty": "intermediate", "prerequisites": [] } ], "goal": "Progress through Association Rule Learning, Semisupervised learning, Batch learning, then wrap with Online learning.", "estimated_minutes": 227 }, { "day": 32, "title": "Day 32", "topics": [ { "name": "instance-based learning", "chapter": "Types of Machine Learning Systems", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "model-based learning", "chapter": "Types of Machine Learning Systems", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Model Selection and Linear Regression", "chapter": "Chapter 1: The Machine Learning Landscape", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Bad Data", "chapter": "Main Challenges of Machine Learning", "summary": "", "difficulty": "beginner", "prerequisites": [] } ], "goal": "Progress through instance-based learning, model-based learning, Model Selection and Linear Regression, then wrap with Bad Data.", "estimated_minutes": 196 }, { "day": 33, "title": "Day 33", "topics": [ { "name": "The Unreasonable Effectiveness of Data", "chapter": "Main Challenges of Machine Learning", "summary": "", "difficulty": "intermediate", "prerequisites": [] }, { "name": "Data Matters More Than Algorithms for Complex Problems", "chapter": "The Unreasonable Effectiveness of Data", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Data Quality Issues", "chapter": "Poor-Quality Data", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Gathering Data and Training a Model", "chapter": "Training and Testing Machine Learning Models", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Testing and Validating Models", "chapter": "Training and Testing Machine Learning Models", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Evaluating Model Performance", "chapter": "Training and Testing Machine Learning Models", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Validation Set Purpose", "chapter": "What is the purpose of a validation set?", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "California Housing Prices Dataset", "chapter": "Chapter 2: End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "A piece of information fed to a Machine Learning system is often called a signal in reference to Shannon's information theory: you want a high signal/noise ratio.", "chapter": "Look at the Big Picture", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Pipelines", "chapter": "Look at the Big Picture", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Problem Framing", "chapter": "Framing the Problem", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Root Mean Square Error (RMSE)", "chapter": "Select a Performance Measure", "summary": "", "difficulty": "beginner", "prerequisites": [] }, { "name": "Insufficient Quantity of Training Data", "chapter": "Instance-Based Versus Model-Based Learning", "summary": "", "difficulty": "beginner", "prerequisites": [ "Main Challenges of Machine Learning" ] }, { "name": "Nonrepresentative Training Data", "chapter": "Instance-Based Versus Model-Based Learning", "summary": "", "difficulty": "beginner", "prerequisites": [ "Main Challenges of Machine Learning" ] }, { "name": "Poor-Quality Data", "chapter": "Instance-Based Versus Model-Based Learning", "summary": "", "difficulty": "beginner", "prerequisites": [ "Main Challenges of Machine Learning" ] }, { "name": "Irrelevant Features", "chapter": "Instance-Based Versus Model-Based Learning", "summary": "", "difficulty": "beginner", "prerequisites": [ "Main Challenges of Machine Learning" ] }, { "name": "Overfitting the Training Data", "chapter": "Instance-Based Versus Model-Based Learning", "summary": "", "difficulty": "beginner", "prerequisites": [ "Main Challenges of Machine Learning" ] }, { "name": "Underfitting the Training Data", "chapter": "Instance-Based Versus Model-Based Learning", "summary": "", "difficulty": "beginner", "prerequisites": [ "Main Challenges of Machine Learning" ] }, { "name": "Exercises", "chapter": "Stepping Back", "summary": "", "difficulty": "beginner", "prerequisites": [ "Testing and Validating" ] }, { "name": "Look at the Big Picture", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Working with Real Data" ] }, { "name": "Better Evaluation Using Cross-Validation", "chapter": "Select and Train a Model", "summary": "", "difficulty": "beginner", "prerequisites": [ "Training and Evaluating on the Training Set" ] }, { "name": "Training a Binary Classifier", "chapter": "3. Classification", "summary": "", "difficulty": "beginner", "prerequisites": [ "MNIST" ] }, { "name": "The Normal Equation", "chapter": "4. Training Models", "summary": "", "difficulty": "beginner", "prerequisites": [ "Linear Regression" ] }, { "name": "Polynomial Regression", "chapter": "Mini-batch Gradient Descent", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Linear Regression" ] }, { "name": "Regularized Linear Models", "chapter": "Mini-batch Gradient Descent", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Linear Regression" ] }, { "name": "Estimating Probabilities", "chapter": "Logistic Regression", "summary": "", "difficulty": "beginner", "prerequisites": [ "Logistic Regression" ] }, { "name": "Training and Cost Function", "chapter": "Logistic Regression", "summary": "", "difficulty": "beginner", "prerequisites": [ "Logistic Regression" ] }, { "name": "Decision Boundaries", "chapter": "Logistic Regression", "summary": "", "difficulty": "beginner", "prerequisites": [ "Logistic Regression" ] }, { "name": "Soft Margin Classification", "chapter": "Support Vector Machines", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Linear SVM Classification" ] }, { "name": "Nonlinear SVM Classification", "chapter": "Support Vector Machines", "summary": "", "difficulty": "advanced", "prerequisites": [ "Linear SVM Classification" ] }, { "name": "Instability", "chapter": "Regression", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Regression" ] }, { "name": "Voting Classifiers", "chapter": "Ensemble Learning and Random Forests", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Regression" ] }, { "name": "Main Approaches for Dimensionality Reduction", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "intermediate", "prerequisites": [ "The Curse of Dimensionality" ] }, { "name": "Installation", "chapter": "Neural Networks and Deep Learning", "summary": "", "difficulty": "beginner", "prerequisites": [ "Up and Running with TensorFlow" ] }, { "name": "Creating Your First Graph and Running It in a Session", "chapter": "Neural Networks and Deep Learning", "summary": "", "difficulty": "beginner", "prerequisites": [ "Up and Running with TensorFlow" ] }, { "name": "Modularity", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "beginner", "prerequisites": [ "Name Scopes" ] }, { "name": "Biological Neurons", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "From Biological to Artificial Neurons" ] }, { "name": "Xavier and He Initialization", "chapter": "Training Deep Neural Nets", "summary": "", "difficulty": "beginner", "prerequisites": [ "Vanishing/Exploding Gradients Problems" ] }, { "name": "Caching the Frozen Layers", "chapter": "Reusing and Tweaking Models", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Freezing the Lower Layers" ] }, { "name": "learning rate", "chapter": "if you have limited computing resources", "summary": "", "difficulty": "intermediate", "prerequisites": [ "online learning" ] }, { "name": "Specifying Model Parameters and Training the Model", "chapter": "Chapter 1: The Machine Learning Landscape", "summary": "", "difficulty": "beginner", "prerequisites": [ "Model Selection and Linear Regression" ] }, { "name": "Handling Outliers and Missing Values", "chapter": "Poor-Quality Data", "summary": "", "difficulty": "beginner", "prerequisites": [ "Data Quality Issues" ] }, { "name": "Feature Engineering", "chapter": "Irrelevant Features", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Data Quality Issues" ] }, { "name": "Choosing Hyperparameters", "chapter": "Training and Testing Machine Learning Models", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Evaluating Model Performance" ] }, { "name": "Avoiding Overfitting", "chapter": "Training and Testing Machine Learning Models", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Evaluating Model Performance" ] }, { "name": "Tuning Hyperparameters with Test Set", "chapter": "What is the purpose of a validation set?", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Validation Set Purpose" ] }, { "name": "Tuning Hyperparameters with Test Set Risks", "chapter": "What can go wrong if you tune hyperparameters using the test set?", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Validation Set Purpose" ] }, { "name": "Supervised Learning Example", "chapter": "Framing the Problem", "summary": "", "difficulty": "beginner", "prerequisites": [ "Problem Framing" ] }, { "name": "Notations", "chapter": "Select a Performance Measure", "summary": "", "difficulty": "beginner", "prerequisites": [ "Root Mean Square Error (RMSE)" ] }, { "name": "A Famous Example of Sampling Bias", "chapter": "The Unreasonable Effectiveness of Data", "summary": "", "difficulty": "beginner", "prerequisites": [ "Nonrepresentative Training Data" ] }, { "name": "Sampling Bias", "chapter": "The Unreasonable Effectiveness of Data", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Nonrepresentative Training Data" ] }, { "name": "Frame the Problem", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Look at the Big Picture" ] }, { "name": "Fine-Tune Your Model", "chapter": "Select and Train a Model", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Better Evaluation Using Cross-Validation" ] }, { "name": "Performance Measures", "chapter": "3. Classification", "summary": "", "difficulty": "beginner", "prerequisites": [ "Training a Binary Classifier" ] }, { "name": "Multiclass Classification", "chapter": "3. Classification", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Training a Binary Classifier" ] }, { "name": "Computational Complexity", "chapter": "4. Training Models", "summary": "", "difficulty": "beginner", "prerequisites": [ "The Normal Equation" ] }, { "name": "Ridge Regression", "chapter": "Mini-batch Gradient Descent", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Linear Regression", "Regularized Linear Models" ] }, { "name": "Lasso Regression", "chapter": "Mini-batch Gradient Descent", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Linear Regression", "Regularized Linear Models" ] }, { "name": "Elastic Net", "chapter": "Mini-batch Gradient Descent", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Linear Regression", "Regularized Linear Models" ] }, { "name": "Bagging and Pasting", "chapter": "Ensemble Learning and Random Forests", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Voting Classifiers" ] }, { "name": "Random Patches and Random Subspaces", "chapter": "Ensemble Learning and Random Forests", "summary": "", "difficulty": "advanced", "prerequisites": [ "Voting Classifiers" ] }, { "name": "Random Forests", "chapter": "Ensemble Learning and Random Forests", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Voting Classifiers" ] }, { "name": "Boosting", "chapter": "Ensemble Learning and Random Forests", "summary": "", "difficulty": "advanced", "prerequisites": [ "Voting Classifiers" ] }, { "name": "Stacking", "chapter": "Ensemble Learning and Random Forests", "summary": "", "difficulty": "advanced", "prerequisites": [ "Voting Classifiers" ] }, { "name": "Projection", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Main Approaches for Dimensionality Reduction" ] }, { "name": "Manifold Learning", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "advanced", "prerequisites": [ "Main Approaches for Dimensionality Reduction" ] }, { "name": "Managing Graphs", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "beginner", "prerequisites": [ "Creating Your First Graph and Running It in a Session" ] }, { "name": "Lifecycle of a Node Value", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "beginner", "prerequisites": [ "Creating Your First Graph and Running It in a Session" ] }, { "name": "Linear Regression with TensorFlow", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "beginner", "prerequisites": [ "Creating Your First Graph and Running It in a Session" ] }, { "name": "Sharing Variables", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "beginner", "prerequisites": [ "Modularity" ] }, { "name": "Logical Computations with Neurons", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "Biological Neurons" ] }, { "name": "Nonsaturating Activation Functions", "chapter": "Training Deep Neural Nets", "summary": "", "difficulty": "beginner", "prerequisites": [ "Xavier and He Initialization" ] }, { "name": "Making Predictions with the Trained Model", "chapter": "Chapter 1: The Machine Learning Landscape", "summary": "", "difficulty": "beginner", "prerequisites": [ "Specifying Model Parameters and Training the Model" ] }, { "name": "Cross-Validation vs Validation Set", "chapter": "What can go wrong if you tune hyperparameters using the test set?", "summary": "", "difficulty": "advanced", "prerequisites": [ "Validation Set Purpose", "Tuning Hyperparameters with Test Set Risks" ] }, { "name": "Select a Performance Measure", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Frame the Problem" ] }, { "name": "Grid Search", "chapter": "Select and Train a Model", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Fine-Tune Your Model" ] }, { "name": "Randomized Search", "chapter": "Select and Train a Model", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Fine-Tune Your Model" ] }, { "name": "Ensemble Methods", "chapter": "Select and Train a Model", "summary": "", "difficulty": "advanced", "prerequisites": [ "Fine-Tune Your Model" ] }, { "name": "Measuring Accuracy Using Cross-Validation", "chapter": "3. Classification", "summary": "", "difficulty": "beginner", "prerequisites": [ "Performance Measures" ] }, { "name": "Confusion Matrix", "chapter": "3. Classification", "summary": "", "difficulty": "beginner", "prerequisites": [ "Performance Measures" ] }, { "name": "Precision and Recall", "chapter": "3. Classification", "summary": "", "difficulty": "beginner", "prerequisites": [ "Performance Measures" ] }, { "name": "The ROC Curve", "chapter": "3. Classification", "summary": "", "difficulty": "beginner", "prerequisites": [ "Performance Measures" ] }, { "name": "Error Analysis", "chapter": "3. Classification", "summary": "", "difficulty": "beginner", "prerequisites": [ "Multiclass Classification" ] }, { "name": "Multilabel Classification", "chapter": "3. Classification", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Multiclass Classification" ] }, { "name": "Gradient Descent", "chapter": "4. Training Models", "summary": "", "difficulty": "beginner", "prerequisites": [ "Computational Complexity" ] }, { "name": "Bagging and Pasting in Scikit-Learn", "chapter": "Ensemble Learning and Random Forests", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Bagging and Pasting" ] }, { "name": "Out-of-Bag Evaluation", "chapter": "Ensemble Learning and Random Forests", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Bagging and Pasting" ] }, { "name": "Extra-Trees", "chapter": "Ensemble Learning and Random Forests", "summary": "", "difficulty": "advanced", "prerequisites": [ "Random Forests" ] }, { "name": "Feature Importance", "chapter": "Ensemble Learning and Random Forests", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Random Forests" ] }, { "name": "AdaBoost", "chapter": "Ensemble Learning and Random Forests", "summary": "", "difficulty": "advanced", "prerequisites": [ "Boosting" ] }, { "name": "Gradient Boosting", "chapter": "Ensemble Learning and Random Forests", "summary": "", "difficulty": "advanced", "prerequisites": [ "Boosting" ] }, { "name": "PCA", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Projection" ] }, { "name": "LLE", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "advanced", "prerequisites": [ "Manifold Learning" ] }, { "name": "Implementing Gradient Descent", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "beginner", "prerequisites": [ "Linear Regression with TensorFlow" ] }, { "name": "Feeding Data to the Training Algorithm", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "beginner", "prerequisites": [ "Linear Regression with TensorFlow" ] }, { "name": "The Perceptron", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "Logical Computations with Neurons" ] }, { "name": "Batch Normalization", "chapter": "Training Deep Neural Nets", "summary": "", "difficulty": "beginner", "prerequisites": [ "Nonsaturating Activation Functions" ] }, { "name": "Check the Assumptions", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Select a Performance Measure" ] }, { "name": "Precision/Recall Tradeoff", "chapter": "3. Classification", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Precision and Recall" ] }, { "name": "Multioutput Classification", "chapter": "3. Classification", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Multilabel Classification" ] }, { "name": "Batch Gradient Descent", "chapter": "4. Training Models", "summary": "", "difficulty": "beginner", "prerequisites": [ "Gradient Descent" ] }, { "name": "Stochastic Gradient Descent", "chapter": "4. Training Models", "summary": "", "difficulty": "beginner", "prerequisites": [ "Gradient Descent" ] }, { "name": "Mini-batch Gradient Descent", "chapter": "Mini-batch Gradient Descent", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Gradient Descent" ] }, { "name": "Preserving the Variance", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "intermediate", "prerequisites": [ "PCA" ] }, { "name": "Principal Components", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "intermediate", "prerequisites": [ "PCA" ] }, { "name": "Projecting Down to d Dimensions", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "intermediate", "prerequisites": [ "PCA" ] }, { "name": "Using Scikit-Learn", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "intermediate", "prerequisites": [ "PCA" ] }, { "name": "Explained Variance Ratio", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "intermediate", "prerequisites": [ "PCA" ] }, { "name": "Choosing the Right Number of Dimensions", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "intermediate", "prerequisites": [ "PCA" ] }, { "name": "PCA for Compression", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "intermediate", "prerequisites": [ "PCA" ] }, { "name": "Incremental PCA", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "advanced", "prerequisites": [ "PCA" ] }, { "name": "Randomized PCA", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "advanced", "prerequisites": [ "PCA" ] }, { "name": "Kernel PCA", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "advanced", "prerequisites": [ "PCA" ] }, { "name": "Manually Computing the Gradients", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Implementing Gradient Descent" ] }, { "name": "Saving and Restoring Models", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "beginner", "prerequisites": [ "Feeding Data to the Training Algorithm" ] }, { "name": "Visualizing the Graph and Training Curves Using TensorBoard", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "beginner", "prerequisites": [ "Feeding Data to the Training Algorithm" ] }, { "name": "Multi-Layer Perceptron and Backpropagation", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "The Perceptron" ] }, { "name": "Gradient Clipping", "chapter": "Training Deep Neural Nets", "summary": "", "difficulty": "beginner", "prerequisites": [ "Batch Normalization" ] }, { "name": "Get the Data", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Check the Assumptions" ] }, { "name": "Selecting a Kernel and Tuning Hyperparameters", "chapter": "Dimensionality Reduction", "summary": "", "difficulty": "advanced", "prerequisites": [ "Kernel PCA" ] }, { "name": "Using autodiff", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Manually Computing the Gradients" ] }, { "name": "Training an MLP with TensorFlow's High-Level API", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "Multi-Layer Perceptron and Backpropagation" ] }, { "name": "Reusing Pretrained Layers", "chapter": "Training Deep Neural Nets", "summary": "", "difficulty": "beginner", "prerequisites": [ "Gradient Clipping" ] }, { "name": "Create the Workspace", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Get the Data" ] }, { "name": "Using an Optimizer", "chapter": "Creating Your First Graph and Running It in a Session", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Using autodiff" ] }, { "name": "Training a DNN Using Plain TensorFlow", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "Training an MLP with TensorFlow's High-Level API" ] }, { "name": "Download the Data", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Create the Workspace" ] }, { "name": "Construction Phase", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "Training a DNN Using Plain TensorFlow" ] }, { "name": "Take a Quick Look at the Data Structure", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Download the Data" ] }, { "name": "Execution Phase", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "Construction Phase" ] }, { "name": "Create a Test Set", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Take a Quick Look at the Data Structure" ] }, { "name": "Using the Neural Network", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "Execution Phase" ] }, { "name": "Discover and Visualize the Data to Gain Insights", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Create a Test Set" ] }, { "name": "Fine-Tuning Neural Network Hyperparameters", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "Using the Neural Network" ] }, { "name": "Visualizing Geographical Data", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Discover and Visualize the Data to Gain Insights" ] }, { "name": "Looking for Correlations", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Discover and Visualize the Data to Gain Insights" ] }, { "name": "Number of Hidden Layers", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "Fine-Tuning Neural Network Hyperparameters" ] }, { "name": "Experimenting with Attribute Combinations", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Looking for Correlations" ] }, { "name": "Number of Neurons per Hidden Layer", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "Number of Hidden Layers" ] }, { "name": "Prepare the Data for Machine Learning Algorithms", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Experimenting with Attribute Combinations" ] }, { "name": "Activation Functions", "chapter": "Introduction to Artificial Neural Networks", "summary": "", "difficulty": "beginner", "prerequisites": [ "Number of Neurons per Hidden Layer" ] }, { "name": "Data Cleaning", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Prepare the Data for Machine Learning Algorithms" ] }, { "name": "Handling Text and Categorical Attributes", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Data Cleaning" ] }, { "name": "Custom Transformers", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Handling Text and Categorical Attributes" ] }, { "name": "Feature Scaling", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "beginner", "prerequisites": [ "Custom Transformers" ] }, { "name": "Transformation Pipelines", "chapter": "2. End-to-End Machine Learning Project", "summary": "", "difficulty": "intermediate", "prerequisites": [ "Feature Scaling" ] } ], "goal": "Progress through The Unreasonable Effectiveness of Data, Data Matters More Than Algorithms for Complex Problems, Data Quality Issues, Gathering Data and Training a Model, Testing and Validating Models, Evaluating Model Performance, Validation Set Purpose, California Housing Prices Dataset, A piece of information fed to a Machine Learning system is often called a signal in reference to Shannon's information theory: you want a high signal/noise ratio., Pipelines, Problem Framing, Root Mean Square Error (RMSE), Insufficient Quantity of Training Data, Nonrepresentative Training Data, Poor-Quality Data, Irrelevant Features, Overfitting the Training Data, Underfitting the Training Data, Exercises, Look at the Big Picture, Better Evaluation Using Cross-Validation, Training a Binary Classifier, The Normal Equation, Polynomial Regression, Regularized Linear Models, Estimating Probabilities, Training and Cost Function, Decision Boundaries, Soft Margin Classification, Nonlinear SVM Classification, Instability, Voting Classifiers, Main Approaches for Dimensionality Reduction, Installation, Creating Your First Graph and Running It in a Session, Modularity, Biological Neurons, Xavier and He Initialization, Caching the Frozen Layers, learning rate, Specifying Model Parameters and Training the Model, Handling Outliers and Missing Values, Feature Engineering, Choosing Hyperparameters, Avoiding Overfitting, Tuning Hyperparameters with Test Set, Tuning Hyperparameters with Test Set Risks, Supervised Learning Example, Notations, A Famous Example of Sampling Bias, Sampling Bias, Frame the Problem, Fine-Tune Your Model, Performance Measures, Multiclass Classification, Computational Complexity, Ridge Regression, Lasso Regression, Elastic Net, Bagging and Pasting, Random Patches and Random Subspaces, Random Forests, Boosting, Stacking, Projection, Manifold Learning, Managing Graphs, Lifecycle of a Node Value, Linear Regression with TensorFlow, Sharing Variables, Logical Computations with Neurons, Nonsaturating Activation Functions, Making Predictions with the Trained Model, Cross-Validation vs Validation Set, Select a Performance Measure, Grid Search, Randomized Search, Ensemble Methods, Measuring Accuracy Using Cross-Validation, Confusion Matrix, Precision and Recall, The ROC Curve, Error Analysis, Multilabel Classification, Gradient Descent, Bagging and Pasting in Scikit-Learn, Out-of-Bag Evaluation, Extra-Trees, Feature Importance, AdaBoost, Gradient Boosting, PCA, LLE, Implementing Gradient Descent, Feeding Data to the Training Algorithm, The Perceptron, Batch Normalization, Check the Assumptions, Precision/Recall Tradeoff, Multioutput Classification, Batch Gradient Descent, Stochastic Gradient Descent, Mini-batch Gradient Descent, Preserving the Variance, Principal Components, Projecting Down to d Dimensions, Using Scikit-Learn, Explained Variance Ratio, Choosing the Right Number of Dimensions, PCA for Compression, Incremental PCA, Randomized PCA, Kernel PCA, Manually Computing the Gradients, Saving and Restoring Models, Visualizing the Graph and Training Curves Using TensorBoard, Multi-Layer Perceptron and Backpropagation, Gradient Clipping, Get the Data, Selecting a Kernel and Tuning Hyperparameters, Using autodiff, Training an MLP with TensorFlow's High-Level API, Reusing Pretrained Layers, Create the Workspace, Using an Optimizer, Training a DNN Using Plain TensorFlow, Download the Data, Construction Phase, Take a Quick Look at the Data Structure, Execution Phase, Create a Test Set, Using the Neural Network, Discover and Visualize the Data to Gain Insights, Fine-Tuning Neural Network Hyperparameters, Visualizing Geographical Data, Looking for Correlations, Number of Hidden Layers, Experimenting with Attribute Combinations, Number of Neurons per Hidden Layer, Prepare the Data for Machine Learning Algorithms, Activation Functions, Data Cleaning, Handling Text and Categorical Attributes, Custom Transformers, Feature Scaling, then wrap with Transformation Pipelines.", "estimated_minutes": 7751 } ] }