conversation_id int64 0 999 | messages listlengths 2 2 |
|---|---|
200 | [
{
"context": "What is the meaning of $V(D,G)$ in the GAN objective function? Here is the GAN objective function.\n$$\\min _{G} \\max _{D} V(D, G)=\\mathbb{E}_{\\boldsymbol{x} \\sim p_{\\text {data }}(\\boldsymbol{x})}[\\log D(\\boldsymbol{x})]+\\mathbb{E}_{\\boldsymbol{z} \\sim p_{\\boldsymbol{z}}(\\boldsymbol{... |
201 | [
{
"context": "Why spend so much time and money to build AIs to play games? I was reading about John McCarthy and his orthodox vision of Artificial Intelligence. To me, it seems like he was not very much in favour of resources (like time and money) being used to make AIs play games like Chess. Instead, he wanted... |
202 | [
{
"context": "Are there neural networks with very few nodes that decently solve non-trivial problems? I'm interested in knowing whether there exist any neural network, that solves (with >=80% accuracy) any nontrivial problem, that uses very few nodes (where 20 nodes is not a hard limit). I want to develop an i... |
203 | [
{
"context": "A mathematical explanation of Attention Mechanism I am trying to understand why attention models are different than just using neural networks. Essentially the optimization of weights or using gates for protecting and controlling cell state (in recurrent networks), should eventually lead to the ne... |
204 | [
{
"context": "When should I use 3D convolutions? I am new to convolutional neural networks, and I am learning 3D convolution. What I could understand is that 2D convolution gives us relationships between low-level features in the X-Y dimension, while the 3D convolution helps detect low-level features and relati... |
205 | [
{
"context": "What is the relationship between gradient accumulation and batch size? I am currently training some models using gradient accumulation since the model batches do not fit in GPU memory. Since I am using gradient accumulation, I had to tweak the training configuration a bit. There are two parameters... |
206 | [
{
"context": "How do mutation and crossover work with real-valued chromosomes? How exactly are \"mutation\" and \"cross-over\" applied in the context of a genetic algorithm based on real numbers (as opposed to just bits)? I think I understood how those two phases are applied in a \"canonical\" context where chr... |
207 | [
{
"context": "Can a technological singularity only occur with superintelligence? In Chapter 26 of the book Artificial Intelligence: A Modern Approach (3rd edition), the textbook discusses \"technological singularity\". It quotes I.J. Good, who wrote in 1965:\n\nLet an ultra-intelligent machine be defined as a m... |
208 | [
{
"context": "Is back-propagation applied for each data point or for a batch of data points? I am new to deep learning and trying to understand the concept of back-propagation. I have a doubt about when the back-propagation is applied. Assume that I have a training data set of 1000 images for handwritten lette... |
209 | [
{
"context": "Why is the merged neural network of AlphaGo Zero more efficient than two separate neural networks? AlphaGo Zero contains several improvements compared to its predecessors. Architectural details of Alpha Go Zero can be seen in this cheat sheet.\nOne of those improvements is using a single neural ne... |
210 | [
{
"context": "What is a deep neural network? What is the definition of a deep neural network? Why are they so popular or important?\n",
"images": null,
"role": "user",
"thinking": null,
"tool_calls": null
},
{
"context": "A deep neural network (DNN) is nothing but a neural network which ... |
211 | [
{
"context": "Is there a trade-off between flexibility and efficiency? A \"general intelligence\" may be capable of learning a lot of different things, but possessing capability does not equal actually having it. The \"AGI\" must learn...and that learning process can take time. If you want an AGI to drive a car... |
212 | [
{
"context": "Why are biases (typically) not used in attention mechanism? Watching this video implementing attention in a transformer. He set query, key, and value biases to False and said \"Typically, people don't use biases for these\".\nEven in official PyTorch code the default bias is False:\n\nadd_bias_kv:... |
213 | [
{
"context": "Are we technically able to make, in hardware, arbitrarily large neural networks with current technology? If neurons and synapses can be implemented using transistors, what prevents us from creating arbitrarily large neural networks using the same methods with which GPUs are made?\nIn essence, we h... |
214 | [
{
"context": "How can an AI freely make decisions? Suppose a deep neural network is created using Keras or Tensorflow. Usually, when you want to make a prediction, the user would invoke model.predict. However, how would the actual AI system proactively invoke their own actions (i.e. without the need for me to c... |
215 | [
{
"context": "Why should the number of neurons in a hidden layer be a power of 2? I have read somewhere on the web (I lost the reference) that the number of units (or neurons) in a hidden layer should be a power of 2 because it helps the learning algorithm to converge faster.\nIs this a fact? If it is, why is t... |
216 | [
{
"context": "How is it that AI can become biased, and what are the proposals to mitigate this? This is not meant to be negative or a joke but rather looking for a productive solution on AI development, engineering and its impact on human life:\nLately with my Google searches, the AI model keeps auto filling th... |
217 | [
{
"context": "Is there any open source counterpart to the IBM Watson? I am looking for something similar to IBM Watson but open source. \n",
"images": null,
"role": "user",
"thinking": null,
"tool_calls": null
},
{
"context": "I am not aware of any open-source products that can readily ... |
218 | [
{
"context": "What kind of problems require more than 2 hidden layers? I've read that the most of the problems can be solved with 1-2 hidden layers.\nHow do you know you need more than 2? For what kind of problems you would need them (give me an example)?\n",
"images": null,
"role": "user",
"thinkin... |
219 | [
{
"context": "Do deep learning algorithms represent ensemble-based methods? According to the Wikipedia article on deep learning:\n\nDeep learning is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing laye... |
220 | [
{
"context": "In Computer Vision, what is the difference between a transformer and attention? Having been studying computer vision for a while, I still cannot understand what the difference between a transformer and attention is?\n",
"images": null,
"role": "user",
"thinking": null,
"tool_calls"... |
221 | [
{
"context": "Why were Chess experts surprised by the AlphaZero's victory against Stockfish? It was recently brought to my attention that Chess experts took the outcome of this now famous match as something of an upset. \nSee: Chess’s New Best Player Is A Fearless, Swashbuckling Algorithm\nAs as a non-expert o... |
222 | [
{
"context": "Do full-text translators such as DeepL or Google Translate fall under the term \"Generative AI\"? My question relates to full-text translators that are not specifically based on LLMs. My current understanding is that the term Generative AI goes beyond LLMs and that the full-text translators (espec... |
223 | [
{
"context": "Why do we prefer ReLU over linear activation functions? The ReLU activation function is defined as follows \n$$y = \\operatorname{max}(0,x)$$\nAnd the linear activation function is defined as follows\n$$y = x$$\nThe ReLU nonlinearity just clips the values less than 0 to 0 and passes everything els... |
224 | [
{
"context": "When did Artificial Intelligence research first start? When did research into Artificial Intelligence first begin? Was it called Artificial Intelligence then or was there another name?\n",
"images": null,
"role": "user",
"thinking": null,
"tool_calls": null
},
{
"context":... |
225 | [
{
"context": "Do self-driving cars resort to randomness to make decisions? I recently heard someone make a statement that when you're designing a self-driving car, you're not building a car but really a computerized driver, so you're trying to model a human mind -- at least the part of the human mind that can d... |
226 | [
{
"context": "Why use ReLU over Leaky ReLU? From my understanding a leaky ReLU attempts to address issues of vanishing gradients and nonzero-centeredness by keeping neurons that fire with a negative value alive.\nWith just this info to go off of, it would seem that the leaky ReLU is just an overall improvement ... |
227 | [
{
"context": "Is AlphaZero an example of an AGI? From DeepMind's research paper on arxiv.org:\n\nIn this paper, we apply a similar but fully generic algorithm, which\n we call AlphaZero, to the games of chess and shogi as well as Go,\n without any additional domain knowledge except the rules of the game,\n d... |
228 | [
{
"context": "Why is the n-step tree backup algorithm an off-policy algorithm? In reinforcement learning book from Sutton & Barto (2018 edition), specifically in section 7.5 of the book, they present an n-step off-policy algorithm that doesn't require importance sampling called n-step tree backup algorithm. \nI... |
229 | [
{
"context": "How powerful a computer is required to simulate the human brain? How much processing power is needed to emulate the human brain? More specifically, the neural simulation, such as communication between the neurons and processing certain data in real-time.\nI understand that this may be a bit of spe... |
230 | [
{
"context": "What are the segment embeddings and position embeddings in BERT? \nThey only reference in the paper that the position embeddings are learned, which is different from what was done in ELMo.\nELMo paper - https://arxiv.org/pdf/1802.05365.pdf\nBERT paper - https://arxiv.org/pdf/1810.04805.pdf\n",
... |
231 | [
{
"context": "How can the emotional quotient of an AI program be measured? Can an AI program have an EQ (emotional intelligence or emotional quotient)?\nIn other words, can the EQ of an AI program be measured?\nIf EQ is more problematic to measure than IQ (at least with a standard applicable to both humans and ... |
232 | [
{
"context": "How can AI researchers avoid \"overfitting\" to commonly-used benchmarks as a community? In fields such as Machine Learning, we typically (somewhat informally) say that we are overfitting if improve our performance on a training set at the cost of reduced performance on a test set / the true popul... |
233 | [
{
"context": "What algorithms are considered reinforcement learning algorithms? What are the areas/algorithms that belong to reinforcement learning?\nTD(0), Q-Learning and SARSA are all temporal-difference algorithms, which belong to the reinforcement learning area, but is there more to it?\nAre the dynamic pro... |
234 | [
{
"context": "Why does Monte Carlo work when a real opponent's behavior may not be random I am learning about Monte Carlo algorithms and struggling to understand the following:\n\nIf simulations are based on random moves, how can the modeling of the opponent's behavior work well?\n\nFor example, if I have a nod... |
235 | [
{
"context": "Was DeepMind's DQN learning simultaneously all the Atari games? DeepMind states that its deep Q-network (DQN) was able to continually adapt its behavior while learning to play 49 Atari games.\nAfter learning all games with the same neural net, was the agent able to play them all at 'superhuman' le... |
236 | [
{
"context": "Are GPT-3.5 series models based on GPT-3? In the official blog post about ChatGPT from OpenAI, there is this paragraph explaining how ChatGPT model was trained:\n\nWe trained this model using Reinforcement Learning from Human Feedback\n(RLHF), using the same methods as InstructGPT, but with slight... |
237 | [
{
"context": "How do I keep track of already visited states in breadth-first search? I was trying to implement the breadth-first search (BFS) algorithm for the sliding blocks puzzle (number type). Now, the main thing I noticed is that, if you have a $4 \\times 4$ board, the number of states can be as large as $... |
238 | [
{
"context": "Is Lisp still worth learning today in the particular context of Machine learning? Lisp was originally created as a practical mathematical notation for computer programs, influenced by the notation of Alonzo Church's lambda calculus. It quickly became the favored programming language for artificial... |
239 | [
{
"context": "What is the difference between encoders and auto-encoders? How are the layers in a encoder connected across the network for normal encoders and auto-encoders? In general, what is the difference between encoders and auto-encoders?\n",
"images": null,
"role": "user",
"thinking": null,
... |
240 | [
{
"context": "What is the difference between expected return and value function? I've seen numerous mathematical explanations of reward, value functions $V(s)$, and return functions. The reward provides an immediate return for being in a specific state. The better the reward, the better the state. \nAs I unders... |
241 | [
{
"context": "Are there any textual CAPTCHA challenges which can fool AI, but not human? Are there any modern techniques of generating textual CAPTCHA (so person needs to type the right text) challenges which can easily fool AI with some visual obfuscation methods, but at the same time human can solve them with... |
242 | [
{
"context": "Are AI winters inevitable? According to Wikipedia (citations omitted):\n\nIn the history of artificial intelligence, an AI winter is a period of reduced funding and interest in artificial intelligence research. The term was coined by analogy to the idea of a nuclear winter. The field has experienc... |
243 | [
{
"context": "Is AI programming useful in everyday programs? I'm curious about Artificial Intelligence. In my regular job, I develop standard applications, like websites with basic functionalities, like user subscription, file upload, or forms saved in a database.\nI mainly know of AI being used in games or rob... |
244 | [
{
"context": "How does AlphaZero's MCTS work when starting from the root node? From the AlphaGo Zero paper, during MCTS, statistics for each new node are initialized as such:\n\n${N(s_L, a) = 0, W (s_L, a) = 0, Q(s_L, a) = 0, P (s_L, a) = p_a}$.\n\nThe PUCT algorithm for selecting the best child node is $a_t = ... |
245 | [
{
"context": "How to use CNN for making predictions on non-image data? I have a dataset which I have loaded as a data frame in Python. It consists of 21392 rows (the data instances, each row is one sample) and 1972 columns (the features). The last column i.e. column 1972 has string type labels (14 different cat... |
246 | [
{
"context": "What is the difference between search and learning? I came across an article, The Bitter Truth, via the Two Minute Papers YouTube Channel. Rich Sutton says...\n\nOne thing that should be learned from the bitter lesson is the great power of general purpose methods, of methods that continue to scale... |
247 | [
{
"context": "How to design a neural network when the number of inputs is variable? I'm looking to design a neural network that can predict which runner wins in a sports game, where the number of runners varies between 2-10. In each case, specific data about the individual runners (for example, the weight, heig... |
248 | [
{
"context": "Why does the \"reward to go\" trick in policy gradient methods work? In the policy gradient method, there's a trick to reduce the variance of policy gradient. We use causality, and remove part of the sum over rewards so that only actions happened after the reward are taken into account (See here h... |
249 | [
{
"context": "What kind of body (if any) does intelligence require? In the mid 1980s, Rodney Brooks famously created the foundations of \"the new AI\". The central claim was that the symbolist approach of 'Good Old Fashioned AI' (GOFAI) had failed by attempting to 'cream cognition off the top', and that embodie... |
250 | [
{
"context": "What is the difference between reinforcement learning and evolutionary algorithms? What is the difference between reinforcement learning (RL) and evolutionary algorithms (EA)?\nI am trying to understand the basics of RL, but I do not yet have practical experience with RL. I know slightly more abou... |
251 | [
{
"context": "What is the benefit of using identity mapping layers in deep neural networks like ResNet? As I understand, ResNet has some identity mapping layers, whose task is to create the output as the same as the input of the layer. The ResNet solved the problem of accuracy degrading. But what is the benefit... |
252 | [
{
"context": "What is the difference between goal-based and utility-based agents? What is the difference between goal-based and utility-based agents? Please, provide a real-world example.\n",
"images": null,
"role": "user",
"thinking": null,
"tool_calls": null
},
{
"context": "Utility is... |
253 | [
{
"context": "Is the expert system still in use today? In my country, the Expert System class is mandatory, if you want to take the AI specialization in most universities. In class, I learned how to make a rule-based system, forward chaining, backward chaining, Prolog, etc.\nHowever, I have read somewhere on th... |
254 | [
{
"context": "How should I represent the input to a neural network for the games of tic-tac-toe, checkers or chess? I've been reading a lot about TD-Gammon recently as I'm exploring options for AI in a video game I'm making. The video game is a turn-based positional sort of game, i.e. a \"units\", or game piece... |
255 | [
{
"context": "Are biological neurons organized in consecutive layers as well? I'm now reading a book titled Hands-On Machine Learning with Scikit-Learn and TensorFlow and in the Chapter 10 of the book, the author writes the following:\n\nThe architecture of biological neural networks (BNN)4 is still the subject... |
256 | [
{
"context": "What is \"early stopping\" in machine learning? What is early stopping in machine learning and, in general, artificial intelligence? What are the advantages of using this method? How does it help exactly?\nI'd be interested in perspectives and links to recent research.\n",
"images": null,
... |
257 | [
{
"context": "What are the limitations of the hill climbing algorithm and how to overcome them? What are the limitations of the hill climbing algorithm? How can we overcome these limitations?\n",
"images": null,
"role": "user",
"thinking": null,
"tool_calls": null
},
{
"context": "As @nb... |
258 | [
{
"context": "Why not cache the Q (query) matrix? Short Version\nWhy do we cache the K (key) and V (value) matrices, but not he Q (query) matrix?\nLong Version\nGiven a toy set of 2-dimensional embedding vectors:\n\n\n\nToken\nEmbedding Vector\n\n\n\n\nquick\n[0.27 0.78]\n\n\nlazy\n[0.38 0.58]\n\n\nbrown\n[0.... |
259 | [
{
"context": "What is ergodicity in a Markov Decision Process (MDP)? I have read about the concept of ergodicity on the safe RL paper by Moldovan (section 3.2) and the RL book by Sutton (chapter 10.3, 2nd paragraph).\nThe first one says that \"a belief over MDPs is ergodic if and only if any state is reachable ... |
260 | [
{
"context": "How can an ensemble be more accurate than the best base classifier in that ensemble? BACKGROUND: Ensemble classifiers are said to reduce bias by taking an \"average\" of predictions of several base classifiers that comprise the ensemble. However, I am uncertain if this necessarily means that the... |
261 | [
{
"context": "How do evolutionary algorithms have advantages over the conventional backpropagation methods? How does employing evolutionary algorithms to design and train artificial neural networks have advantages over using the conventional backpropagation algorithms?\n",
"images": null,
"role": "user"... |
262 | [
{
"context": "What is the difference between the positional encoding techniques of the Transformer and GPT? I know the original Transformer and the GPT (1-3) use two slightly different positional encoding techniques.\nMore specifically, in GPT they say positional encoding is learned. What does that mean? OpenAI... |
263 | [
{
"context": "Are ReLUs incapable of solving certain problems? Background\nI've been interested in and reading about neural networks for several years, but I haven't gotten around to testing them out until recently.\nBoth for fun and to increase my understanding, I tried to write a class library from scratch in... |
264 | [
{
"context": "Using AI to extend an imagine pattern I have created some nice patterns using the MidJourney tool. I'd like to find a way to extend these patterns, and I was thinking about an AI tool that takes one of these patterns and extends it in all directions surrounding the original pattern.\nJust to give ... |
265 | [
{
"context": "What are some resources on computational learning theory? Pretty soon I will be finishing up Understanding Machine Learning: From Theory to Algorithms by Shai Ben-David and Shai Shalev-Shwartz. I absolutely love the subject and want to learn more, the only issue is I'm having trouble finding a boo... |
266 | [
{
"context": "A deep learning algorithm to optimize the outcome I'm am quite new to deep learning but I think I found just the right real-world situation to start using it. The problem is that I have only used such algorithms to predict outcomes. For my new project, I need information to feed a machine with to... |
267 | [
{
"context": "How does using ASIC for the acceleration of AI work? We can read on Wikipedia page that Google built a custom ASIC chip for machine learning and tailored for TensorFlow which helps to accelerate AI.\nSince ASIC chips are specially customized for one particular use without the ability to change its... |
268 | [
{
"context": "What are the biggest barriers to get RL in production? I am studying the state of the art of Reinforcement Learning, and my point is that we see so many applications in the real world using Supervised and Unsupervised learning algorithms in production, but I don't see the same thing with Reinforce... |
269 | [
{
"context": "Why class embedding token is added to the Visual Transformer? In the famous work on the Visual Transformers, the image is split into patches of a certain size (say 16x16), and these patches are treated as tokens in the NLP tasks. In order to perform classification, a CLS token is added at the begi... |
270 | [
{
"context": "Loss jumps abruptly when I decay the learning rate with Adam optimizer in PyTorch I'm training an auto-encoder network with Adam optimizer (with amsgrad=True) and MSE loss for Single channel Audio Source Separation task. Whenever I decay the learning rate by a factor, the network loss jumps abrupt... |
271 | [
{
"context": "Can machine learning algorithms be used to differentiate between small differences in details between images? I was wondering if machine learning algorithms (CNNs?) can be used/trained to differentiate between small differences in details between images (such as slight differences in shades of red... |
272 | [
{
"context": "What is a support vector machine? What is a support vector machine (SVM)? Is an SVM a kind of a neural network, meaning it has nodes and weights, etc.? What is it best used for?\nWhere I can find information about these?\n",
"images": null,
"role": "user",
"thinking": null,
"tool_c... |
273 | [
{
"context": "What is the concept of channels in CNNs? I am trying to understand what channels mean in convolutional neural networks. When working with grayscale and colored images, I understand that the number of channels is set to 1 and 3 (in the first conv layer), respectively, where 3 corresponds to red, gr... |
274 | [
{
"context": "What benefits can be got by applying Graph Convolutional Neural Network instead of ordinary CNN? What benefits can we got by applying Graph Convolutional Neural Network instead of ordinary CNN? I mean if we can solve a problem by CNN, what is the reason should we convert to Graph Convolutional Neu... |
275 | [
{
"context": "What is the double sample problem in reinforcement learning? According to the SBEED: Convergent Reinforcement Learning with\nNonlinear Function Approximation for convergent reinforcement learning, the Smoothed Bellman operator is a way to dodge the double sample problem? Can someone explain to me ... |
276 | [
{
"context": "Are decision tree learning algorithms deterministic? Are decision tree learning algorithms deterministic? Given a fixed dataset, do they always produce a tree with the same structure? \nWhat about the random forest?\n",
"images": null,
"role": "user",
"thinking": null,
"tool_calls"... |
277 | [
{
"context": "What causes ChatGPT to generate responses that refer to itself as a bot or LM? ChatGPT occasionally generates responses to prompts that refer to itself as a \"bot\" or \"language model.\"\nFor instance, when given a certain input (the first paragraph of this question) ChatGPT produces (in part) th... |
278 | [
{
"context": "Can Q-learning be used in a POMDP? Can Q-learning (and SARSA) be directly used in a Partially Observable Markov Decision Process (POMDP)? If not, why not? My intuition is that the policies learned will be terrible because of partial observability. Are there ways to transform these algorithms so th... |
279 | [
{
"context": "How to transform inputs and extract useful outputs in a Neural Network? So I've been trying to understand neural networks ever since I came across Adam Geitgey's blog on machine learning. I've read as much as I can on the subject (that I can grasp) and believe I understand all the broad concepts a... |
280 | [
{
"context": "What are the necessary components to make an AI agent capable of self-programming? An AI agent is often thought of having \"sensors\", \"a memory\", \"machine learning processors\" and \"reaction\" components. However, a machine with these does not necessarily become a self-programming AI agent. B... |
281 | [
{
"context": "Should I use anthropomorphic language when discussing AI? The English Language is not well-suited to talking about artificial intelligence, which makes it difficult for humans to communicate to each other about what an AI is actually \"doing\". Thus, it may make more sense to use \"human-like\" te... |
282 | [
{
"context": "Does AlphaZero use Q-Learning? I was reading the AlphaZero paper Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm, and it seems they don't mention Q-Learning anywhere.\nSo does AZ use Q-Learning on the results of self-play or just a Supervised Learning?\nIf it... |
283 | [
{
"context": "What is the cost function of a transformer? The paper Attention Is All You Need describes the transformer architecture that has an encoder and a decoder.\nHowever, I wasn't clear on what the cost function to minimize is for such an architecture.\nConsider a translation task, for example, where giv... |
284 | [
{
"context": "What are the criteria for a system to be considered intelligent? For example, could you provide reasons why a sundial is not \"intelligent\"?\nA sundial senses its environment and acts rationally. It outputs the time. It also stores percepts. (The numbers the engineer wrote on it.)\nWhat properti... |
285 | [
{
"context": "Is there an AI model for generating sarcastic sentences? I am currently working on an Android AI app. \nI am aware of AI models to generate random sentences. However, is there an AI model for generating sarcastic sentences?\n",
"images": null,
"role": "user",
"thinking": null,
"too... |
286 | [
{
"context": "What does the symbol $\\mathbb E$ mean in these equations? I came across some papers that use $\\mathbb E$ in equations, in particular, this paper: https://arxiv.org/pdf/1511.06581.pdf. Here is some equations from the paper that uses it: \n$Q^\\pi \\left(s,a \\right) = \\mathbb E \\left[R_t|s_t = ... |
287 | [
{
"context": "What's the term for death by dissolving in AI? What's the term (if such exists) for merging with AI (e.g. via neural lace) and becoming so diluted (e.g. 1:10000) that it effectively results in a death of the original self?\nIt's not quite \"digital ascension\", because that way it would still be y... |
288 | [
{
"context": "What happens when I mix activation functions? There are several activation functions, such as ReLU, sigmoid or $\\tanh$. What happens when I mix activation functions?\nI recently found that Google has developed Swish activation function which is (x*sigmoid). By altering activation function can it ... |
289 | [
{
"context": "How big artificial neural networks can we run now if our total energy budget for computation is equivalent to the human brain energy budget? How big artificial neural networks can we run now (either with full train-backprop cycle or just evaluating network outputs) if our total energy budget for c... |
290 | [
{
"context": "What is the difference between a stationary and a non-stationary policy? In reinforcement learning, there are deterministic and non-deterministic (or stochastic) policies, but there are also stationary and non-stationary policies. \nWhat is the difference between a stationary and a non-stationary ... |
291 | [
{
"context": "What are the different approaches used in Machine Learning? There seem to be so many sub-fields, so I'm interested in getting a better understanding of the approaches.\nI'm looking for information on a single framework per answer, in order to allow for granularity without the overall answer gettin... |
292 | [
{
"context": "Why is cross-over a part of genetic algorithms? Genetic Algorithms has come to my attention recently when trying to correct/improve computer opponents for turn-based strategy computer games.\nI implemented a simple Genetic Algorithm that didn't use any cross-over, just some random mutation. It see... |
293 | [
{
"context": "Can Bayesian inference be combined with knowledge-based systems? I've been struggling with the connection between knowledge-based AI systems and Bayesian inference for a while now. While I continue to sweep through the literature, I would be happy if someone can answer these more specific question... |
294 | [
{
"context": "What is the formula for the momentum and Adam optimisers? In the gradient descent algorithm, the formula to update the weight $w$, which has $g$ as the partial gradient of the loss function with respect to it, is:\n$$w\\ -= r \\times g$$\nwhere $r$ is the learning rate.\nWhat should be the formula... |
295 | [
{
"context": "What are some examples of intelligent agents for each intelligent agent class? There are several classes of intelligent agents, such as:\n\nsimple reflex agents\nmodel-based reflex agents\ngoal-based agents\nutility-based agents\nlearning agents\n\nEach of these agents behaves slightly different f... |
296 | [
{
"context": "What are some resources with exercises related to neural networks? I am asking for a book (or any other online resource) where we can solve exercises related to neural networks, similar to the books or online resources dedicated to mathematics where we can solve mathematical exercises.\n",
"im... |
297 | [
{
"context": "What are some resources on continuous state and action spaces MDPs for reinforcement learning? Most introductions to the field of MDPs and Reinforcement learning focus exclusively on domains where space and action variables are integers (and finite). This way we are introduced quickly to Value Ite... |
298 | [
{
"context": "How can I predict the next number in a non-obvious sequence? I've got an array of integers ranging from -3 to +3.\nExample: [1, 3, -2, 0, 0, 1]\nThe array has no obvious pattern since it represents bipolar disorder mood swings.\nWhat is the most suitable approach to predict the next number in the ... |
299 | [
{
"context": "Are there reinforcement learning algorithms that scale to large problems? Given a large problem, value iteration and other table based approaches seem to require too many iterations before they start to converge. Are there other reinforcement learning approaches that better scale to large problems... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.