Split (1)

train · 1k rows

conversation_id int64 0 999	messages listlengths 2 2
800	[ { "context": "Relevance of Weisfeiler–Lehman Graph Isomorphism Test limitation for Graph Neural Networks Graph Neural Networks power is limited by the power of Weisfeiler–Lehman Graph Isomorphism algorithm.\nQuoting wikipedia:\n\nIt has been demonstrated that GNNs cannot be more expressive than the\nWeisfeiler–...
801	[ { "context": "What could happen if we wrongly assume that the POMDP is an MDP? Consider the Breakout environment.\nWe know that the underlying world behaves like an MDP, because, for the evolution of the system, it just needs to know what the current state (i.e. position, speed, and speed direction of the ball,...
802	[ { "context": "Is reinforcement learning only about determining the value function? I started reading some reinforcement learning literature, and it seems to me that all approaches to solving reinforcement learning problems are about finding the value function (state-value function or action-state value function...
803	[ { "context": "What are the most instructive movies about artificial intelligence? The field of AI has expanded profoundly in recent years, as has public awareness and interest. This includes the arts, where fiction about AI has been popular since at least Isaac Asimov. Films on various subjects can be good tea...
804	[ { "context": "Why do neural nets and machine learning tend to work well with MCTS, but not with regular Minimax game-playing AI? I've often heard MCTS grouped together with neural nets and machine learning. From what I gather, MCTS uses a refined intuition (from maching learning) to evaluate positions. This all...
805	[ { "context": "Does backpropagation update weights one layer at a time? I am new to Deep Learning.\nSuppose that we have a neural network with one input layer, one output layer, and one hidden layer. Let's refer to the weights from input to hidden as $W$ and the weights from hidden to output as $V$. Suppose that...
806	[ { "context": "What is the calcium equivalent role in neural networks I understand that neural networks model biological neurons. Each node in the network represents a neuron cell and the connections between nodes represent the connections between cells. As in nature, a neuron fires an electrical signal to con...
807	[ { "context": "How can I detect datetime patterns in text? I want to explore and experiment the ways in which I could use a neural network to identify patterns in text. \nexamples:\n\nPrices of XYZ stock went down at 11:00 am today\nRetrieve a list of items exchanged on 03/04/2018\nShow error logs between 3 - 5 ...
808	[ { "context": "Concrete example of latent variables and observables plugged into the Bayes' rule In the context of the variational auto-encoder, can someone give me a concrete example of the application of the Bayes' rule\n$$p_{\\theta}(z\|x)=\\frac{p_{\\theta}(x\|z)p(z)}{p(x)}$$\nfor a given latent variable and o...
809	[ { "context": "How to compute the action probabilities with Thompson sampling in deep Q-learning? In some implementations of off-policy Q-learning, we need to know the action probabilities given by the behavior policy $\\mu(a)$ (e.g., if we want to use importance sampling).\nIn my case, I am using Deep Q-Learnin...
810	[ { "context": "How to verify classification model trained on classification dataset on a detection dataset for classification purpose? I am working on a problem that involves two tasks - detection and classification. There is no single dataset for both tasks. I am training two models, separate on detection datas...
811	[ { "context": "How does an unsupervised learning model learn? How does an unsupervised learning model learn, if it does not involve any target values?\n", "images": null, "role": "user", "thinking": null, "tool_calls": null }, { "context": "Supervised learning is typically an attempt to l...
812	[ { "context": "Is it possible to combine two neural networks trained on different tasks into one that knows both tasks? I'm relatively new to artificial intelligence and neural networks.\nLet's say I have two different fully trained neural networks. The first one is trained for mathematical addition and the seco...
813	[ { "context": "When is a knowledge base consistent? I am studying a knowledge base (KB) from the book \"Artificial Intelligence: A Modern Approach\" (by Stuart Russell and Peter Norvig) and from this series of slides.\nA formula is satisfiable if there is some assignment to the variables that makes the formula e...
814	[ { "context": "Why does having a fixed policy change a Markov Decision Process to a Markov Reward Process? If a policy is fixed, it is said that a Markov Decision Process (MDP) becomes a Markov Reward Process (MRP).\nWhy is this so? Aren't the transitions and rewards still parameterized by the action and current...
815	[ { "context": "Use cross-validation to train after model selection I have been recently reading about model selection algorithms (for example to decide which value of the regularisation parameter or what size of a neural network to use, broadly hyper-parameters). This is done by dividing the examples into three ...
816	[ { "context": "Does MMD-VAE solve the problem of blurred images of vanilla VAEs? I understand that with vanilla VAEs, there are a few reasons justifying the production of blurred out images. The InfoVAE paper describes the case when the decoder is flexible enough to ignore the latent attributes and generate an a...
817	[ { "context": "Which machine learning approach should I use to estimate how many products a research group should have to improve its category? Currently, in my country, there is a system in which certain groups of researchers upload information on products of scientific interest, such as research articles, book...
818	[ { "context": "Is case-based reasoning a machine learning technique? A few years ago when I was in university, I had implemented (for my final year project) an Itinerary Planning System, which incorporates an AI technique called \"case-based reasoning\".\nIs case-based reasoning a machine learning technique or a...
819	[ { "context": "Are there any microchips specifically designed to run ANNs? I'm interested in hardware implementation of ANNs (artificial neural networks). Are there any popular existing technology implementations in form of microchips which are purpose designed to run artificial neural networks? For example, a c...
820	[ { "context": "Are on-line backpropagation iterations perpendicular to the constraint? Raul Rojas' Neural Networks A Systematic Introduction, section 8.1.2 relates off-line backpropagation and on-line backpropagation with Gauss-Jacobi and Gauss-Seidel methods for finding the intersection of two lines.\nWhat I ca...
821	[ { "context": "What is the gradient of the objective function in the Soft Actor-Critic paper? In the paper Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor, they define the loss function for the policy network as\n$$\nJ_\\pi(\\phi)=\\mathbb E_{s_t\\sim \\mathcal D...
822	[ { "context": "Why is Batch Gradient Descent performing worse than Stochastic and Mini-Batch Gradient Descent? I have implemented a neural network from scratch (only using numpy) and I am having problems understanding why the results are so different between Stochastic/Mini-Batch Gradient Descent and Batch Gradi...
823	[ { "context": "How does the \"Lorem Ipsum\" generator work? I've seen many Lorem Ipsum generators on the web, but not only, there is also \"bacon ispum\", \"space ispum\", etc. So, how do these generators generate the text? Are they powered by an AI?\n", "images": null, "role": "user", "thinking": nu...
824	[ { "context": "What type of neural network would be most feasible for playing a realtime game? For implementing a neural network algorithm that can play air hockey, I had two ideas for input, and I'm trying to figure out which design would be most viable.\nThe output must be two analog values that dictate the be...
825	[ { "context": "Are Bayesian networks important to learn in 2018? I study AI by myself with the book \"Artificial Intelligence: A Modern Approach\". I've just finished the chapters about the Bayesian network and probabilities, and I found them very interesting. Now, I want to implement different algorithms and te...
826	[ { "context": "Should we also shuffle the test dataset when training with SGD? When training machine learning models (e.g. neural networks) with stochastic gradient descent, it is common practice to (uniformly) shuffle the training data into batches/sets of different samples from different classes. Should we als...
827	[ { "context": "How would you encode your input vector/matrix from a sequence of moves in game like tasks to train an AI? e.g. Chess AI? I've seen data sets for classification / regressions tasks in domains such as credit default detection, object identification in an image, stock price prediction etc. All of th...
828	[ { "context": "Why should we study causation in artificial intelligence? Judea Pearl won the 2011 Turing Award\n\nFor fundamental contributions to artificial intelligence through the development of a calculus for probabilistic and causal reasoning.\n\nHe is credited with the invention of Bayesian networks and a ...
829	[ { "context": "Expected SARSA vs SARSA in \"RL: An Introduction\" Sutton and Barto state in the 2018-version of \"Reinforcement Learning: An Introduction\" in the context of Expected SARSA (p. 133) the following sentences:\n\nExpected SARSA is more complex computationally than Sarsa but, in return, it eliminates...
830	[ { "context": "Proof of Maximization Bias in Q-learning? In the textbook \"Reinforcement Learning: An Introduction\" by Richard Sutton and Andrew Barto, the concept of Maximization Bias is introduced in section 6.7, and how Q-learning \"over-estimates\" action-values is discussed using an example. However, a for...
831	[ { "context": "What should the initial UCT value be with MCTS, when leaf's simulation count is zero? Infinity? I am implenting a Monte Carlo Tree Search algorithm, where the selection process is done through Upper Confidence Bound formula:\ndef uct(state):\n log_n = math.log(state.parent.sim_count) \n ...
832	[ { "context": "Why isn't my decision tree classifier able to solve the XOR problem properly? I was trying to solve an XOR problem, and the dataset seems like the one in the image.\n\nI plotted the tree and got this result:\n\nAs I understand, the tree should have depth 2 and four leaves. The first comparison is ...
833	[ { "context": "What is the typical AI approach for solving blackjack? I'm currently developing a blackjack program. Now, I want to create an AI that essentially uses the mathematics of blackjack to make decisions. \nSo, what is the typical AI approach for solving blackjack?\nIt doesn't have to be language-specif...
834	[ { "context": "Why do we discount the state distribution? In Reinforcement Learning, it is common to use a discount factor $\\gamma$ to give less importance to future rewards when calculating the returns.\nI have also seen mention of discounted state distributions. It is mentioned on page 199 of the Sutton and B...
835	[ { "context": "Which Reinforcement Learning algorithms are efficient for episodic problems? I have some episodic datasets extracted from a turn-based RTS game in which the current actions leading to the next state doesn’t determine the final solution/outcome of the episode.\nThe learning is expected to terminate...
836	[ { "context": "Is it practical to train AlphaZero or MuZero (for indie games) on a personal computer? Is it practical/affordable to train an AlphaZero/MuZero engine using a residential gaming PC, or would it take thousands of years of training for the AI to learn enough to challenge humans?\nI'm having trouble w...
837	[ { "context": "Is deep learning merely experimental? I am an undergraduate student majoring in Computer Science. I am currently about to graduate, so I need to decide on my future path. During my junior and senior years, I took many courses related to deep learning and artificial intelligence. However, I don’t f...
838	[ { "context": "Why object detection algorithms are poor in optical character recognition? OCR is still a very hard problem. We don't have universal powerful solutions. We use the CTC loss function\nAn Intuitive Explanation of Connectionist Temporal Classification \| Towards Data Science\nSequence Modeling\nWith C...
839	[ { "context": "Do AlphaZero/MuZero learn faster in terms of number of games played than humans? I don't know much about AI and am just curious.\nFrom what I read, AlphaZero/MuZero outperform any human chess player after a few hours of training. I have no idea how many chess games a very talented human chess play...
840	[ { "context": "Meaning of Actor Output in Actor Critic Reinforcement Learning In actor critic, The equations for calculating the loss in actor critic are an \nactor loss (parameterized by $\\theta$) \n$$log[\\pi_\\theta(s_t,a_t)]Q_w(s_t,a_t)$$ \nand a critic loss (parameterized by $w$) \n$$r(s_t,a_t) + \\gamma Q...
841	[ { "context": "Constructing a dataset that scores well only for a specific set of hyper parameter values When designing a machine-learning system, there are various parameters that have to be determined. I am interested in the following general question: is it possible to construct a dataset on which the system ...
842	[ { "context": "Modern reinforcement learning for video game NPCs Recently, I have been reading about the 1996 artificial life game 'Creatures'. The game features NPCs called 'Norns' that use reinforcement learning to learn continuously through interactions with the player and their environment. From what I have ...
843	[ { "context": "Do good approximations produce good gradients? Let’s say I have a neural net doing classification and I’m doing stochastic gradient descent to train it. If I know that my current approximation is a decent approximation, can I conclude that my gradient is a decent approximation of the gradient of t...
844	[ { "context": "How can my Q-learning agent trained to solve a specific maze generalize to other mazes? I implemented Q-learning to solve a specific maze. However, it doesn't solve other mazes. How could my Q-learning agent be able to generalize to other mazes?\n", "images": null, "role": "user", "thi...
845	[ { "context": "Eligibility vector for softmax policy with policy gradients There is this nice result for policy gradients that the gradient of some performance measure, $\\nabla v_{\\pi_{\\theta}}(s_0)$ (here, in the episodic case for the starting state $s_0$ and policy $\\pi$, parametrised by some weights $\\th...
846	[ { "context": "Is it possible to build an AI that learns humanity, morally? It is a new era and people are trying to evolve more in science and technology. Artificial Intelligent is one of the ways to achieve this. We have seen lots of examples for AI sequences or a simple \"communication AI\" that are able to t...
847	[ { "context": "Are there any approaches to AGI that will definitely not work? Is there empirical evidence that some approaches to achieving AGI will definitely not work? For the purposes of the question the system should at least be able to learn and solve novel problems.\nSome possible approaches:\n\nA Prolog p...
848	[ { "context": "Is it possible to recognise a person based on what they have written? I needed to make a system for recognizing people based on hundreds of texts by finding similarities in their written text grammatically or similarities between words they choose for writing. I don't want it so accurate, but I wa...
849	[ { "context": "Intuitively understanding translational invariance in CNNs I'm currently in the process of learning about using CNNs in image recognition. Many of the different resources I read that were explaining the motivation referred to the fact that these networks are (to some degree) translationally invari...
850	[ { "context": "How to implement an Automatic Learning Rate for a Neural Network? I'm learning Neural Networks, and everything works as planned but, like humans do, adjusting themselves to learn more efficiently, I'm trying to understand conceptually how one might implement an auto adjusting learning rate for a N...
851	[ { "context": "How can the generalization error be estimated? How would you estimate the generalization error? What are the methods of achieving this?\n", "images": null, "role": "user", "thinking": null, "tool_calls": null }, { "context": "Generalization error is the error obtained by ap...
852	[ { "context": "Should the reward or the Q value be clipped for reinforcement learning When extending reinforcement learning to the continuous states, continuous action case, we must use function approximators (linear or non-linear) to approximate the Q-value. It is well known that non-linear function approximat...
853	[ { "context": "Could AI kill the joy of competitive sports and games? Lee Sedol, former world champion, and legendary Go player today announced his retirement with the quote \"Even if I become the No. 1, there is an entity that cannot be defeated\".\nIs it possible that AIs could kill the joy of competitive game...
854	[ { "context": "Is there a reason to use TensorFlow over PyTorch for research purposes? I've been using PyTorch to do research for a while and it seems to be quite easy to implement new things with. Also, it is easy to learn and I didn't have any problem with following other researchers code so far.\nHowever, I ...
855	[ { "context": "What makes the approximation capabilities of neural networks different than something like, say, Fourier series? People often cite the universal approximation theorem as a reason for why neutral networks are so effective at capturing patterns or features of various training data. However, this see...
856	[ { "context": "Should I use minimax or alpha-beta pruning? Should I use minimax or alpha-beta pruning (or both)? Apparently, alpha-beta pruning prunes some parts of the search tree. \n", "images": null, "role": "user", "thinking": null, "tool_calls": null }, { "context": "Both algorithms ...
857	[ { "context": "Which problems in information security can be solved better using neural networks? Information security has become a thriving field during the last years. It is a broad domain ranging from planing and building over testing to operating different applications, systems and networks in a secure fashi...
858	[ { "context": "Why do Decision Tree Learning Algorithm preferably outputs the smallest Decision Tree? I have been following the ML course by Tom Mitchel. \nThe inherent assumption while using Decision Tree Learning Algo is: The algo. preferably chooses a Decision Tree which is the smallest. \nWhy is this so when...
859	[ { "context": "How do I statistically evaluate a ML model? I have a model that predicts sentiment of tweets. Are there any standard procedures to evaluate such a model in terms of its output?\nI could sample the output, work out which are correctly predicted by hand, and count true and false positives and negati...
860	[ { "context": "How would I compute the optimal state-action value for a certain state and action? I am currently trying to learn reinforcement learning and I started with the basic gridworld application. I tried Q-learning with the following parameters:\n\nLearning rate = 0.1\nDiscount factor = 0.95\nExploration...
861	[ { "context": "Why is the stationary distribution independent of the initial state in the proof of the policy gradient theorem? I was going through the proof of the policy gradient theorem here: https://lilianweng.github.io/lil-log/2018/04/08/policy-gradient-algorithms.html#svpg \nIn the section \"Proof of Polic...
862	[ { "context": "Mathematical foundations of the ability to learn I am an undergraduate student in applied mathematics with an interest in artificial intelligence. I am currently exploring topics where I could do research. Coming from a mathematical background I am interested in the question: Can we mathematically...
863	[ { "context": "Why would neural networks be a particularly good framework for \"embodied AI\"? There is this claim around that the brain's cognitive capabilities are tightly linked to the way it processes sensorimotor information and that, in this or a similar sense, our intelligence is \"embodied\". Lets assume...
864	[ { "context": "Why does REINFORCE work at all? Here's a screenshot of the popular policy-gradient algorithm from Sutton and Barto's book -\n\nI understand the mathematical derivation of the update rule - but I'm not able to build intuition as to why this algorithm should work in the first place. What really both...
865	[ { "context": "Approaches to an algorithm for crossing a road I want to write an algorithm which indicates to a robot the first point in time when it is reasonably safe to cross a road. Assume that the robot's goal is to travel to a location that requires a road crossing and that the robot is ready to cross.\nS...
866	[ { "context": "Can hidden Markov models be used to model any time series data? Can HMMs be used to model any time series data? Or does the data have to be that of a Markov process?\nIn HTK documentation, I see that the first few lines state that it can model any time series \n\nHTK is a toolkit for building Hidd...
867	[ { "context": "What is the importance of the endocannabinoid system for cognitive function? The endocannabinoid system is a very important function of human biology. Unfortunately, due to the illegality of cannabis, it is a relatively new field of study. I have read a few articles about Google researching the ro...
868	[ { "context": "Can CNNs be made robust to tricks where small changes cause misclassification? I while ago I read that you can make subtle changes to an image that will ensure a good CNN will horribly misclassify the image. I believe the changes must exploit details of the CNN that will be used for classification...
869	[ { "context": "What is a probability distribution in machine learning? If we were learning or working in the machine learning field, then we frequently come across the term \"probability distribution\". I know what probability, conditional probability, and probability distribution/density in math mean, but what ...
870	[ { "context": "Is there a reason to choose regular momentum over Nesterov momentum for neural networks? I've been reading about Nesterov momentum from here and it seems like a nice improvement over regular momentum with no extra cost whatsoever.\nHowever, is this really the case? Are there instances where regula...
871	[ { "context": "Could an AI be sentient? In theory, could an AI become sentient, as in learning and becoming self-aware, all from its source code?\n", "images": null, "role": "user", "thinking": null, "tool_calls": null }, { "context": "In theory, if one could build a computing device that...
872	[ { "context": "Do we know what the units of neural networks will do before we train them? I was learning about back-propagation and, looking at the algorithm, there is no particular 'partiality' given to any unit. What I mean by partiality there is that you have no particular characteristic associated with any u...
873	[ { "context": "How can I use Neural Network in motion identification I'm quite new to image processing and AI. But I have the expertise to create a network that can be used in object detection and recognition. Most of the time I've used ANN or Naive Bayes.\nNow, I want to develop a method of action recognition, ...
874	[ { "context": "Is a decision tree less suitable for incremental learning than e.g. a neural net? I can recall that a professor once said that decision trees are not good for incremental learning, as they have to be rebuilt from the ground up if new training examples arrive.\n\nIs this basically true? Quick googl...
875	[ { "context": "Why does the pass@k metric not \"behave like\" probability? pass@k is a metric used to evaluate models that generate code, used for example to evaluate Codex. To evaluate pass@k, you have a dataset of natural language/code pairs, and you pass each NL prompt to the model. For each prompt, it genera...
876	[ { "context": "Why does Q-learning converge under 100% exploration rate? I am working on this assignment where I made the agent learn state-action values (Q-values) with Q-learning and 100% exploration rate. The environment is the classic gridworld as shown in the following picture.\n\nHere are the values of my ...
877	[ { "context": "How can I determine the mathematical relation between the input and output variables? I would like to take in some input values for $n$ variables, say $R$, $B$, and $G$. Let $Y$ denote the response variable of these $n$ inputs (in this example, we have $3$ inputs). Other than these, I would like t...
878	[ { "context": "Are model-free and off-policy algorithms the same? In respect of RL, is model-free and off-policy the same thing, just different terminology? If not, what are the differences? I've read that the policy can be thought of as 'the brain', or decision making part, of machine learning application, wher...
879	[ { "context": "What is a trap function in the context of a genetic algorithm? What is a trap function in the context of a genetic algorithm? How is it related to the concepts of local and global optima?\n", "images": null, "role": "user", "thinking": null, "tool_calls": null }, { "context...
880	[ { "context": "Can ML/AI understand incomplete constructs like humans? We have AI's predicting images, predicting objects in an image. Understanding audio, meaning of the audio if it is a spoken sentence.\nIn humans when we start seeing a movie halfway through, we still understand the entire movie (although this...
881	[ { "context": "Is the word \"pose\" used correctly in the paper \"Matrix Capsules with EM Routing\"? In traditional computer vision and computer graphics, the pose matrix is a $4 \\times 4$ matrix of the form \n$$\n\\begin{bmatrix}\nr_{11} & r_{12} & r_{12} & t_{1} \\\\\nr_{21} & r_{22} & r_{22} & t_{...
882	[ { "context": "Is logistic regression more free from the conditional independence assumption than naive Bayes? To my understanding, logistic regression is an extension of naive Bayes. \nSuppose $X = \\{x_1, x_2, \\dots, x_N \\}$ and $Y = \\{0, 1\\}$, each $x_i$ is i.i.d and $P(x_i \\mid Y=y_k) \\sim \\mathcal{N}...
883	[ { "context": "Why is the Chinese Room argument such a big deal? I've been re-reading the Wikipedia article on the Chinese Room argument and I'm... actually quite unimpressed by it. It seems to me to be largely a semantic issue involving the conflation of various meanings of the word \"understand\". Of course, s...
884	[ { "context": "Why did the developement of neural networks stop between 50s and 80s? In a video lecture on the development of neural networks and the history of deep learning (you can start from minute 13), the lecturer (Yann LeCunn) said that the development of neural networks stopped until the 80s because peop...
885	[ { "context": "Why do DQNs tend to forget? Why do DQNs tend to forget? Is it because when you feed highly correlated samples, your model (function approximation) doesn't give a general solution?\nFor example:\n\nI use level 1 experiences, my model $p$ is fitted to learn how to play that level.\n\nI go to level 2...
886	[ { "context": "How powerful is OpenAI's Gym and Universe in board games area? I'm a big fan of computer board games and would like to make Python chess/go/shogi/mancala programs. Having heard of reinforcement learning, I decided to look at OpenAI Gym.\nBut first of all, I would like to know, is it possible using...
887	[ { "context": "What is a \"closed expression\" in the context of logic? I was reading about logic systems and the following phrase appeared.\n\nany closed expression that is not derivable inside the same system\n\nWhat is a \"closed expression\" in this context? What does \"closed expression that is not derivabl...
888	[ { "context": "In TD(0) with linear function approximation, why is the gradient of $\\hat v(S^{\\prime}, \\mathbf w)$ wrt parameters $\\mathbf w$ not considered? I am reading these slides. On page 38, the update for the parameters for the linear function approximation of TD(0) is given. I have a doubt regarding ...
889	[ { "context": "What beginner-friendly machine learning method should I use to make teams for my pickup ultimate frisbee club fairly balanced? A bunch of friends and I play ultimate every week. Recently I wrote a program to choose our teams for us, as well as keep track of certain data (like which players were on...
890	[ { "context": "Can exogenous variables be state features in reinforcement learning? I have a question about state representation of Q-learning or DQN algorithm.\nI'm still a beginner of RL, so I'm not sure that is it suitable to take exogenous variables as state features.\nFor example, in my current project, dec...
891	[ { "context": "How does the NEAT speciation algorithm work? I've been reading up on how NEAT (Neuro Evolution of Augmenting Topologies) works and I've got the main idea of it, but one thing that's been bothering me is how you split the different networks into species. I've gone through the algorithm but it doesn...
892	[ { "context": "Why did AlphaGo lose its Go game? We can read on wiki page that in March 2016 AlphaGo AI lost its game (1 of 5) to Lee Sedol, a professional Go player. One article cite says:\n\nAlphaGo lost a game and we as researchers want to explore that and find out what went wrong. We need to figure out what ...
893	[ { "context": "Do we use validation and test sets for training a reinforcement learning agent? I am pretty new to reinforcement learning and was working with some code for the PPO and DQN algorithms. After looking at the code, I noticed that the authors did not include any code to setup a validation or testing d...
894	[ { "context": "Why does a Lipschitz continuous discriminator in GANs assure statistical boundedness? I have been reading the paper which introduced spectral normalization in GANs.\nAt some point the paper mentions the following:\n\nThe machine learning community has been pointing out recently that the\n functio...
895	[ { "context": "In Q-learning, wouldn't it be better to simply iterate through all possible states? In Q-learning, all resources I've found seem to say that the algorithm to update the Q-table should start at some initial state, and pick actions (which are sometimes random) to explore the state space.\nHowever, w...
896	[ { "context": "Why does the activation function for a hidden layer in a MLP have to be non-polynomial? Across multiple pieces of literature describing MLPs or while describing the universal approximation theorem, the statement is very specific on the activation function being non-polynomial.\nIs there a reason w...
897	[ { "context": "How does the VAE learn a joint distribution? I found the following paragraph from An Introduction to\nVariational Autoencoders sounds relevant, but I am not fully understanding it.\n\nA VAE learns stochastic mappings between an observed $\\mathbf{x}$-space, whose empirical distribution $q_{\\mathc...
898	[ { "context": "Which NLP techniques can be used to transform sentences (e.g. from passive to active voice) without affecting their meaning? I'm looking for NLP techniques to transform sentences without affecting their meaning.\nFor example, techniques that could transform active voice into passive voice, such as...
899	[ { "context": "Is pooling a kind of dropout? If I got well the idea of dropout, it allows improving the sparsity of the information that comes from one layer to another by setting some weights to zero.\nOn the other hand, pooling, let's say max-pooling, takes the maximum value in a neighborhood, reducing as well...

Subsets and Splits

No community queries yet

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