Split (1)

train · 1k rows

conversation_id int64 0 999	messages listlengths 2 2
700	[ { "context": "How does AI 'see' the images it generates- from what perspective? I've been using AI image generation for a while now, and I've noticed how profoundly AI doesn't seem to see the image as a whole, sometimes generating an image with parts of fingers floating near objects supposed to be being held, V...
701	[ { "context": "How to detect frauds in advertising business using machine learning? I am very beginner to this world. I still learning the basics of Machine learning and AI but i have a problem at hand and i am not sure which technique or Algorithm can be applied on it.\nI am working on Click-Fraud detection in ...
702	[ { "context": "What does the notation $\\mathcal{N}(z; \\mu, \\sigma)$ stand for in statistics? I know that the notation $\\mathcal{N}(\\mu, \\sigma)$ stands for a normal distribution.\nBut I'm reading the book \"An Introduction to Variational Autoencoders\" and in it, there is this notation:\n$$\\mathcal{N}(z; ...
703	[ { "context": "Why is it called back-propagation? While looking at the mathematics of the back-propagation algorithm for a multi-layer perceptron, I noticed that in order to find the partial derivative of the cost function with respect to a weight (say $w$) from any of the hidden layers, we're just writing the e...
704	[ { "context": "DQN arXiv 10-year anniversary: What are the outstanding problems being actively researched in deep Q-learning since 2019? Background\nAs of today (12-19-2023), the arXiv submission of the original deep Q-learning approach to achieve superhuman performance on ATARI games has turned a decade old. Th...
705	[ { "context": "Why would someone use NEAT over other machine learning algorithms? Why would someone use a neuroevolution algorithm, such as NEAT, over other machine learning algorithms? What situation would only apply to an algorithm such as NEAT, but no other machine learning algorithm?\n", "images": null, ...
706	[ { "context": "Emulating human brain - with analogous NN chips Considering the answers of this question, emulating a human brain with the current computing capacity is currently impossible, but we aren't very far from it.\nNote, 1 or 2 decades ago, similar calculations had similar results.\nThe clock frequency o...
707	[ { "context": "Why doesn't SiLU suffer from a worse version of a \"dying ReLU\" problem? Unlike ReLU, the derivative of SiLU is non-zero everywhere except at the global minimum. However, intuitively it seems like having a negative gradient when the input is very negative should be even worse than having a zero g...
708	[ { "context": "When should one prefer using Total Variational Divergence over KL divergence in RL In RL, both the KL divergence (DKL) and Total variational divergence (DTV) are used to measure the distance between two policies. I'm most familiar with using DKL as an early stopping metric during policy updates to...
709	[ { "context": "How are afterstate value functions mathematically defined? In this answer, afterstate value functions are mentioned, and that temporal-difference (TD) and Monte Carlo (MC) methods can also use these value functions. Mathematically, how are these value functions defined? Yes, they are a function of...
710	[ { "context": "What is the intuition behind variational inference for Bayesian neural networks? I'm trying to understand the concept of Variational Inference for BNNs. My source is this work. The aim is to minimize the divergence between the approx. distribution and the true posterior\n$$\\text{KL}(q_{\\theta}(w...
711	[ { "context": "Is it possible for an AI to learn how to speak from books as training sets? I want to know something more about it. Are there any github repo or an open source project?\n", "images": null, "role": "user", "thinking": null, "tool_calls": null }, { "context": "It is possible\...
712	[ { "context": "How can artificial intelligence (including deep learning algorithms) find suspicious patterns in the body’s biochemistry? It has been suggested that machine learning algorithms (also Watson) can help with finding disease in patient images and optimize scans. Also that deep learning algorithms show...
713	[ { "context": "Why is the mean used to compute the expectation in the GAN loss? From Goodfellow et al. (2014), we have the adversarial loss:\n$$ \\min_G \\, \\max_D V (D, G) = \\mathbb{E}_{x∼p_{data}(x)} \\, [\\log \\, D(x)] + \\, \\mathbb{E}_{z∼p_z(z)} \\, [\\log \\, (1 − D(G(z)))] \\, \\text{.} \\quad$$\nIn p...
714	[ { "context": "What are methods human actors use to imitate robots? Robot technology is usually thought from an engineering perspective. A human programmer writes a software this executed in a robot who is doing a task. \nBut what would happen, if the project is started with the opposite goal? The idea is, that ...
715	[ { "context": "In the Manifold Hypothesis applied to LLMs, are text sequences points or paths on the manifold? The Manifold Hypothesis makes a ton of sense to me for images. Images are points in high dimensional space, where each dimension corresponds to the intensity value of a single pixel. For example, we can...
716	[ { "context": "Why do all states appear identical under the function approximation in the Short Corridor task? This is the Short Corridor problem taken from the Sutton & Barto book. Here it's written:\n\nThe problem is difficult because all the states appear identical under the function approximation\n\nBut this...
717	[ { "context": "How to calculate the distance between the camera and an object using Computer Vision? I want to create a Deep Learning model that measures the distance between the camera and certain objects in an image. Is it possible? Please, let me know some resources related to this task.\n", "images": nul...
718	[ { "context": "What are the major differences between cost, loss, error, fitness, utility, objective, criterion functions? I find the terms cost, loss, error, fitness, utility, objective, criterion functions to be interchangeable, but any kind of minor difference explained is appreciated.\n", "images": null,...
719	[ { "context": "What does Brooks mean by \"representation\"? For a class, I'm reading Brooks' \"Intelligence without representation\". The introduction is dedicated to slating representation as a focus for AI development.\nI've read that representation is the problem of representing information symbolically, in t...
720	[ { "context": "Is PyTorch's `grad_fn` for a non-differentiable function that function's inverse? What is grad_fn for a non-differentiable function like slicing (grad_fn=<SliceBackward0>), view (grad_fn=<ViewBackward0>), etc.? Is grad_fn simply the function's inverse operation?\nWhere in the source code can I see...
721	[ { "context": "Can a crossover result in a node with no outgoing connections? I'm currently implementing the original NEAT algorithm in Swift.\nLooking at figure 4 in Stanley's original paper, it seems to me there is a chance that node 5 will have no (enabled) outgoing connection if parent 1 is assumed the fitte...
722	[ { "context": "What is a beam? For example, faster-whisper's transcribe function takes an argument\nbeam_size: Beam size to use for decoding.\n\nWhat does \"beam\" mean?\n", "images": null, "role": "user", "thinking": null, "tool_calls": null }, { "context": "Beam search\nThe beam search ...
723	[ { "context": "What is Statistical relational learning? I have gone through the wikipedia explanation of SRL. But, it only confused me more:\n\nStatistical relational learning (SRL) is a subdiscipline of artificial intelligence and machine learning that is concerned with domain models that exhibit both uncertain...
724	[ { "context": "How do weak learners become strong in boosting? Boosting refers to a family of algorithms which converts weak learners to strong learners. How does it happen?\n", "images": null, "role": "user", "thinking": null, "tool_calls": null }, { "context": "As @desertnaut mentioned ...
725	[ { "context": "Examples of ontologies made with AI I'm looking for more or less successful artificial intelligence usage examples to build an ontology or rationale why it can't be done. I found a lot of articles on how to use ontologies for AI, but not succeded vice versa.\n", "images": null, "role": "us...
726	[ { "context": "Which neural network can count the number of objects in an image? I'm looking for a neural network architecture that excels in counting objects. For example, CNN that can output the number of balls (or any other object) in a given image.\nI already found articles about crowd counting. I'm looking ...
727	[ { "context": "Where can I find pre-trained language models in English and German? Where can I find (more) pre-trained language models? I am especially interested in neural network-based models for English and German.\nI am aware only of Language Model on One Billion Word Benchmark and TF-LM: TensorFlow-based La...
728	[ { "context": "Are neurons in layer $l$ only affected by neurons in the previous layer? Are artificial neurons in layer $l$ only affected by those in layer $l-1$ (providing inputs) or are they also affected by neurons in layer $l$ (and maybe by neurons in other layers)?\n", "images": null, "role": "user"...
729	[ { "context": "Neural networks of arbitrary/general topology? Usually neural networks consist from layers, but is there research effort that tries to investigate more general topologies for connections among neurals, e.g. arbitrary directed acyclic graphs (DAGs).\nI guess there can be 3 answers to my question:\n...
730	[ { "context": "Are calculus and differential geometry required for building neural networks? I've been studying geometry and linear algebra for months with the goal to build neural networks. But now I'm reading that perceptrons require fitting curves, and curves are not expressed as linear functions. So, I might...
731	[ { "context": "How to make convnets aware what the image actually is, not what is depicted on it? I've uploaded a picture to Wolfram's ImageIdentify of graffiti on the wall, but it recognized it as 'monocle'. Secondary guesses were 'primate', 'hominid', and 'person', so not even close to 'graffiti' or 'painting'...
732	[ { "context": "Should the policy parameters be updated at each time step or at the end of the episode in REINFORCE? REINFORCE is a Monte Carlo policy gradient algorithm, which updates weights (parameters) of policy network by generating episodes. Here's a pseudo-code from Sutton's book (which is same as the equa...
733	[ { "context": "Why not use the MSE instead of the current logistic regression? When watching the machine learning course on Coursera by Andrew Ng, in the logistic regression week, the cost function was a bit more complex than the one for linear regression, but definitely not that hard. \nBut it got me thinking, ...
734	[ { "context": "Are the model implementations in Hugging Face’s transformers library created by the original model authors or by Hugging Face? I've been exploring the implementation of models like Llama in Hugging Face’s transformers library, for example:\nHugging Face's Llama model implementation.\nI’m curious a...
735	[ { "context": "Variable Number of Inputs to Neural Networks So suppose that you have a real estate appraisal problem. You have some structured data, and some images exterior of home, bedrooms, kitchen, etc. The number of pictures taken is variable per observational unit, i.e. the house.\nI understand the basics ...
736	[ { "context": "What is a \"batch\" in batch normalization? I'm working on an example of CNN with the MNIST hand-written numbers dataset. Currently I've got convolution -> pool -> dense -> dense, and for the optimiser I'm using Mini-Batch Gradient Descent with a batch size of 32.\nNow this concept of batch normal...
737	[ { "context": "What's the optimal policy in the rock-paper-scissors game? A deterministic policy in the rock-paper-scissors game can be easily exploited by the opponent - by doing just the right sequence of moves to defeat the agent. More often than not, I've heard that a random policy is the optimal policy in t...
738	[ { "context": "What's the difference between a \"perceptron\" and a GLM? In a comment to this question user nbro comments:\n\nAs a side note, \"perceptrons\" and \"neural networks\" may not be the same thing. People usually use the term perceptron to refer to a very simple neural network that has no hidden layer...
739	[ { "context": "How to replicate legacy systems with machine learning? Let's suppose that we have a legacy system in which we don't have the source code and this system is on a mainframe written in Cobol. Is there any way using machine learning in which we can learn from the inputs and outputs the way the executa...
740	[ { "context": "What does 'democratizing AI' exactly mean? In my AI literature research, I often notice authors use the term 'democratizing AI', especially in the AutoML area. For example in the abstract (last sentence) of this paper:\n\nLEAF therefore forms a foundation for democratizing and improving AI, as wel...
741	[ { "context": "How can we prove that an autoassociator network will continue to perform if we zero the diagonal elements of a weight matrix? How can we prove that an auto-associator network will continue to perform if we zero the diagonal elements of a weight matrix that has been determined by the Hebb rule? In ...
742	[ { "context": "Which function $(\\hat{y} - y)^2$ or $(y - \\hat{y})^2$ should I use to compute the gradient? The MSE can be defined as $(\\hat{y} - y)^2$, which should be equal to $(y - \\hat{y})^2$, but I think their derivative is different, so I am confused of what derivative will I use for computing my gradie...
743	[ { "context": "In reinforcement learning, does the optimal value correspond to performing the best action in a given state? I am confused about the definition of the optimal value ($V^$) and optimal action-value (Q) in reinforcement learning, so I need some clarification, because some blogs I read on Medium an...
744	[ { "context": "How to set the target for the actor in A2C? I did a simple Actor-Critic implementation in Keras using 2 networks where the critic learns the Q-Values of every action, and the actor predicts probabilities for choosing each action. In training, the target probabilities for the actor was a one-hot ve...
745	[ { "context": "How to parse conjunctions in natural language processing? Is there an accepted way in NLP to parse conjunctions (and/or) in a sentence?\nBy following the example below, how would I parse\n\nI drink orange juice if its the weekend or if it's late and I'm tired.\n\ninto\n\nit's the weekend\n\nand \n...
746	[ { "context": "While fine-tuning a decoder only LLM like LLaMA on chat dataset, what kind of padding should one use? While fine-tuning a decoder only LLM like LLaMA on chat dataset, what kind of padding should one use?\nMany papers use Left Padding, but is right padding wrong since transformers gives the followi...
747	[ { "context": "Does IBM Watson use machine learning? I was reading an article on Medium and wanted to make it clear whether a bot created on IBM Watson is an intelligent one or unintelligent.\n\nSimply put, there are 2 types of chatbots — unintelligent ones that act using predefined conversation flows (algorithm...
748	[ { "context": "How many weights does the max-pooling layer have? How many weights does the max-pooling layer have?\nFor example, if there are 10 inputs, a pooling filter of size 2, stride 2, how many weights, including bias, does a max-pooling layer have?\n", "images": null, "role": "user", "thinking...
749	[ { "context": "Should the prediction of the body temperature given a camera image be modelled as classification or regression? I am fairly new to deep learning in general and I am currently facing a problem I want to solve using neural networks and I am unsure if it is a classification or regression problem. I a...
750	[ { "context": "Understanding the equation of TD(0) in the paper \"Learning to predict by the methods of temporal differences\" In the paper Learning to predict by the methods of temporal differences (p. 15), the weights in the temporal difference learning are updated as given by the equation\n$$\n\\Delta w_t\n= ...
751	[ { "context": "Type of artificial neural network suitable for learning and then predicting forest growth I'm trying to use an ANN to learn from a large amount of forest measurement data obtained from sampling plots across Ontario, Canada and associated climate data provided by regional climate modelling in this ...
752	[ { "context": "Can neural networks with a sigmoid as the activation function of the output layer approximate continuous functions? Neural networks are commonly used for classification tasks, in fact from this post it seems like that's where they shine brightest. \nHowever, when we want to classify using neural ...
753	[ { "context": "Snake game: snake converges to going in the same direction every time This is a q-learning snake using a neural network as a q function aproximator and I'm losing my mind here the current model it's worst than the initial one.\nThe current model uses a 32x32x32 MLPRegressor from scikit-learn using...
754	[ { "context": "What are examples of approaches to dimensionality reduction of feature vectors? Given a pre-trained CNN model, I extract feature vector of images in reference and query dataset with several thousands of elements.\nI would like to apply some augmentation techniques to reduce the feature vector dime...
755	[ { "context": "Why is symbolic AI not so popular as ANN but used by IBM's Deep Blue? Everybody is implementing and using DNN with, for example, TensorFlow or PyTorch.\nI thought IBM's Deep Blue was an ANN-based AI system, but this article says that IBM's Deep Blue was symbolic AI.\nAre there any special features...
756	[ { "context": "Which linear algebra book should I read to understand vectorized operations? I am reading Goodfellow's book about neural networks, but I am stuck in the mathematical calculus of the back-propagation algorithm. I understood the principle, and some Youtube videos explaining this algorithm shown step...
757	[ { "context": "What is the effect of mislabeled training data? Collecting and labeling training data for supervised learning tasks is incredibly time-consuming and costly.\nFor instance, let's say you wrote a script that went on Google images and got you 5000 pictures for each of 10 classes. You then use an unsu...
758	[ { "context": "Is there any resource that describes in detail a naive example-based machine translation algorithm? I'm looking to develop a machine translation tool for a constructed language. I think that the example-based approach is the most suitable because the said language is very regular and I can have a ...
759	[ { "context": "Is the 'direction' considered, when determining the branching factor in bidirectional search? If I am correct, the branching factor is the maximum number of successors of any node.\nWhen I am applying bidirectional search to a transition graph like this one below\n\nIf 11 is the goal state and I s...
760	[ { "context": "Why does the variational auto-encoder use the reconstruction loss? VAE is trained to reduce the following two losses.\n\nKL divergence between inferred latent distribution and Gaussian.\n\nthe reconstruction loss\n\n\nI understand that the first one regularizes VAE to get structured latent space. ...
761	[ { "context": "What part of the game is the value network trained to predict a winner on? The Alpha Zero (as well as AlphaGo Zero) papers say they trained the value head of the network by \"minimizing the error between the predicted winner and the game winner\" throughout its many self-play games. As far as I co...
762	[ { "context": "What is \"Computational Linguistics\"? It's not clear to me whether or not someone whose work aims to improve an NLP system may be called a \"Computational Linguist\" even when she/he doesn't modify the algorithm directly by coding.\nLet's consider the following activities:\nAnnotation for Machine...
763	[ { "context": "How does L2 regularization make weights smaller? I'm learning logistic regression and $L_2$ regularization.\nThe cost function looks like below.\n$$J(w) = -\\displaystyle\\sum_{i=1}^{n} (y^{(i)}\\log(\\phi(z^{(i)})+(1-y^{(i)})\\log(1-\\phi(z^{(i)})))$$\nAnd the regularization term is added. ($\\la...
764	[ { "context": "What is the relationship between fuzzy logic and objective bayesian probability? I understand fuzzy logic is a variant of formal logic where, instead of just 0 or 1, a given sentence may have a truth value in the [0..1] interval. Also, I understand that logical probability (objective bayesian) und...
765	[ { "context": "Is there a way to perform pattern recognition without a labeled training set? I have a 10GB file of a time series 1D signal. I want to find some patterns within this signal, I know CNN's are great for this but the problem is I don't have any training data.\nNow, I could, of course, spend an entire...
766	[ { "context": "Why is dialogue a hard problem in natural language processing? I've just started learning natural language processing from Dan Jurafsky's videos lectures. In that video, minute 4:56, he is stating that dialogue is a hard problem in natural language processing (NLP). Why?\n", "images": null, ...
767	[ { "context": "Use ConvNet to predict bitmap I want to build a classifier which takes an aerial image and outputs a bitmap. The bitmap is supposed to be 1 at every pixel where the aerial image has water. For this process I want to use a ConvNet but I am unsure about the output layer. I identified two approaches:...
768	[ { "context": "Why is the research on artificial intelligence at this stage all researching on a separate ability? Why is the research on artificial intelligence at this stage all researching on a separate ability? For example, train the visual ability of the computer alone, train the speech recognition ability ...
769	[ { "context": "How do LLMs tokenize python (significant whitespace) I was learning about tokenization (WordPiece) and how there is a normalization step prior to that that will remove consecutive whitespace from the input text, since these are not significant normally.\nBut that got we wonder\n\nhow do LLMs still...
770	[ { "context": "How to detect a full-fledged self-aware AI? The premise: A full-fledged self-aware artificial intelligence may have come to exist in a distributed environment like the internet. The possible A.I. in question may be quite unwilling to reveal itself.\nThe question: Given a first initial suspicion, h...
771	[ { "context": "Is there a neural network with a varying number of neurons? Is there some type of neural network that changes the number of neurons while training? \nUsing this idea, the network can increase or decrease the number of neurons when the complexity of the inputs increases or decreases.\n", "image...
772	[ { "context": "How does text classification reduce manpower costs? (I apologize for the title being too broad and the question being not 'technical')\nSuppose that my task is to label news articles. This means that given a news article, I am supposed to classify which category that news belong to. Eg, 'Ronaldo s...
773	[ { "context": "Trying to understand VGG convolution neural networks architecture Trying to understand the VGG architecture and I have these following questions.\n\nI understand the general understanding of increasing filter size is because we are using max pooling and so its image size gets reduced. So in order ...
774	[ { "context": "How do we test if an model or algorithm is AI-complete? How do we test if a model or algorithm is AI-complete?\n", "images": null, "role": "user", "thinking": null, "tool_calls": null }, { "context": "According to the Wikipedia definition, a problem is said to be AI-complet...
775	[ { "context": "What kind of algorithm is used by StackGAN to generate realistic images from text? What kind of algorithm is used by StackGAN to generate realistic images from text? How does StackGAN work?\n", "images": null, "role": "user", "thinking": null, "tool_calls": null }, { "conte...
776	[ { "context": "Why exactly was previously believed that the deterministic policy gradient did not exist? I'm reading the paper Deterministic Policy Gradient Algorithms, David Silver et al.\nFirst of all, in the introduction, the author says that\n\nIt was previously believed that the deterministic policy gradien...
777	[ { "context": "Why Are the Standard and Markov Chain Derivations of the Policy Gradient Theorem Equivalent? While studying the proof of the Policy Gradient Theorem, I have come across two different approaches.\nThe first seems to be a more standard approach involving \"unrolling\" across every time step. A good ...
778	[ { "context": "Should we fear an AGI if it will be equivalent to a human? It seems to me that the first AGIs ought to be able to perform the same sort and variety of tasks as people, with the most computationally strenuous tasks taking an amount of time compared to how long a person would take. If this is the ca...
779	[ { "context": "How can I apply reinforcement learning to solve this asteroid game? Introduction\nAn attractive asteroid game was described in the paper Learning Policies for Embodied Virtual Agents through Demonstration (2017, Jonathan Dinerstein et al.):\n\nIn our first experiment, the virtual agent is a spaces...
780	[ { "context": "How can I avoid overfitting when doing parameter tuning? I very often applied a grid search to tune the parameters of my supervised model. I have the feeling that parameter tuning will eventually (very often) lead to overfitting? Is this crazy to say?\nIs there a way that we can apply grid search ...
781	[ { "context": "Does the input layer of a neural network have bias and are there bias neurons? I have seen two different representations of neural networks when it comes to bias. Consider a \"simple\" neural network, with just an input layer, a hidden layer and an output layer. To compute the value of a neuron in...
782	[ { "context": "Is it possible to separately evolve a part of the population? In a classic example of a genetic algorithm, you would have a population and a certain amount of simulation time to evaluate it and breeding. Then proceed to the next generation.\nIs it possible, during the simulation process, to have a...
783	[ { "context": "How can I generate \"what\", \"why\" and \"who\" types of questions from question templates? I was wondering if in any way it is possible to generate $n$ questions based on gap-fill-in type questions.\nFor example, the following template\n\n______ is a process in which plants generate energy.\n\nc...
784	[ { "context": "Why are neural networks so data hungry? Stephen Wolfram published an interesting long post on machine learning this week.\nHe illustrates a function approximation application with the following target function, piecewise flat with three regions.\n\nI understand one can describe such a function wit...
785	[ { "context": "What applications of smooth manifold theory exist to Artificial Intelligence? What applications of smooth manifold theory exist to Artificial Intelligence?\nI have some knowledge of smooth manifold theory, and was wondering how I could apply it to a project on Artificial Intelligence. In particula...
786	[ { "context": "How does policy evaluation work for continuous state space model-free approaches? How does policy evaluation work for continuous state space model-free approaches?\nTheoretically, a model-based approach for the discrete state and action space can be computed via dynamic programming and solving the...
787	[ { "context": "Shouldn't Gödel's incompleteness theorems disprove the physical symbol system hypothesis? According to the Wikipedia page of the physical symbol system hypothesis (PSSH), this hypothesis seems to be a vividly debated topic in philosophy of AI. But, since it's about formal systems, shouldn't it be ...
788	[ { "context": "What is the meaning of the square brackets in ant colony optimization? I'm studying the paper \"Minimizing Total Tardiness on a Single Machine Using Ant Colony Optimization\" which has proposed to use Ant colony optimization to SMTWTP.\nAccording to this paper:\n\nEach artificial ant iteratively a...
789	[ { "context": "What is the difference between DQN and AlphaGo Zero? I have already implemented a relatively simple DQN on Pacman.\nNow I would like to clearly understand the difference between a DQN and the techniques used by AlphaGo zero/AlphaZero and I couldn't find a place where the features of both approache...
790	[ { "context": "How to calculate the advantage in policy gradient functions? From my understanding of the REINFORCE policy gradient method, we gently nudge the probabilities of actions based on the advantages. More specifically, the positive advantages increase the probabilities, negative advantages reduce the pr...
791	[ { "context": "Why does the clipped surrogate objective work in Proximal Policy Optimization? In Proximal Policy Optimization Algorithms (2017), Schulman et al. write\n\nWith this scheme, we only ignore the change in probability ratio when it would make the objective improve, and we include it when it makes the ...
792	[ { "context": "Machine learning applied to space-time diagrams of cellular automata I wonder if machine learning has ever been applied to space-time diagrams of cellular automata. What comprises a training set seems clear: a number of space-time diagrams of one or several (elementary) cellular automata. For a su...
793	[ { "context": "What are examples of machine learning techniques inspired by neuroscience? What are examples of machine learning techniques (i.e. models, algorithms, etc.) inspired (to different extents) by neuroscience?\nParticularly, I'm interested in recent developments, say less than 10 years old, that have t...
794	[ { "context": "How to detect vanishing gradients? Can vanishing gradients be detected by the change in distribution (or lack thereof) of my convolution's kernel weights throughout the training epochs? And if so how?\nFor example, if only 25% of my kernel's weights ever change throughout the epochs, does that imp...
795	[ { "context": "Deep Q-Learning: why don't we use mini-batches during experience reply? In examples and tutorial about DQN, I've often noticed that during the experience replay (training) phase people tend to use stochastic gradient descent / online learning. (e.g. link1, link2) \n# Sample minibatch from the memo...
796	[ { "context": "How does being on-policy prevent us from using the replay buffer with the policy gradients? \nOne of the approaches to improving the stability of the Policy\nGradient family of methods is to use multiple environments in\nparallel. The reason behind this is the fundamental problem we\ndiscussed in ...
797	[ { "context": "In OCR, how should I deal with the warped text on the sides of oval objects? Consider an image that contains one can (or bottle, or any similar oval object), which has texts all over it. In the image below, I have many bottles, but you can assume that each image only contains one such object.\n\nA...
798	[ { "context": "What jobs cannot be automatized by AI in the future? AI is progressing drastically, and imagine they tell you you're fired because a robot will take your place. What are some jobs that can never be automated?\n", "images": null, "role": "user", "thinking": null, "tool_calls": null ...
799	[ { "context": "What are the differences between an agent that thinks rationally and an agent that acts rationally? Stuart Russell and Peter Norvig pointed out 4 four possible goals to pursue in artificial intelligence: systems that think/act humanly/rationally.\nWhat are the differences between an agent that thi...

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.