Hottest Questions This Month

8 votes

1 answer

1k views

What do symmetric weights mean and how does it make backpropagation biologically implausible?

neural-networks backpropagation

CommunityBot

1

modified May 10 at 4:21

3 votes

2 answers

45 views

Why doesn't the inception score measure intra-class diversity

generative-adversarial-networks inception

Edoardo Guerriero

3,433

answered May 6 at 14:55

2 votes

1 answer

147 views

Is it appropriate to represent 'total failure' as an absorbing state?

reinforcement-learning markov-decision-process state-spaces transition-model episodic-tasks

nbro

33k

modified May 15 at 14:57

2 votes

1 answer

181 views

How does learning the moves of chess show up in a neural network?

neural-networks machine-learning chess

nbro

33k

answered May 14 at 11:07

4 votes

1 answer

59 views

Does the term "data augmentation" imply increasing the training dataset?

machine-learning reference-request terminology data-preprocessing data-augmentation

nbro

33k

modified Apr 23 at 9:04

2 votes

1 answer

67 views

How to construct a reward function for a "wait and see" problem

reinforcement-learning reference-request terminology reward-functions reward-design

nbro

33k

modified Apr 28 at 14:28

1 vote

2 answers

49 views

Given a set of trajectories produced by a fixed policy, what is the the standard approach to estimate Q?

reinforcement-learning algorithm-request monte-carlo-methods temporal-difference-methods

Raphael Lopez Kaufman

183

modified May 12 at 18:36

-1 votes

1 answer

102 views

can't find a viable import class for keras.utils.Sequence [closed]

tensorflow keras

desertnaut

926

modified May 3 at 14:51

1 vote

1 answer

46 views

What is the difference between features and inputs in machine learning?

machine-learning comparison terminology features

nbro

33k

modified May 17 at 10:06

0 votes

3 answers

74 views

How to deal with an unbalanced dataset?

neural-networks machine-learning datasets feedforward-neural-networks imbalanced-datasets

nbro

33k

modified Apr 30 at 14:41

-1 votes

1 answer

47 views

What is so special about the Bellman Optimality Principle?

reinforcement-learning bellman-equations

Raphael Lopez Kaufman

183

answered May 9 at 19:44

-1 votes

1 answer

59 views

Denoise autoencoder not training properly [closed]

convolutional-neural-networks keras autoencoders vgg denoising-autoencoder

arizona_3

1

modified Apr 28 at 11:37

1 vote

0 answers

75 views

How are 4D cost volumes constructed for DL based stereo matching?

deep-learning computer-vision papers stereo-matching

Manuel Maior

11

modified May 6 at 19:15

4 votes

1 answer

58 views

Why is it important/beneficial for an activation function to be zero-meaned?

neural-networks deep-learning activation-functions

Chillston

166

modified May 10 at 0:34

0 votes

1 answer

54 views

Is there way to segment an image without labeling/classification, as well as supervised learning?

machine-learning reference-request object-detection image-segmentation algorithm-request

Adrian Evensen

11

answered Apr 29 at 10:11

0 votes

2 answers

42 views

How to represent multi-label colours in one-hot encoding?

neural-networks machine-learning natural-language-processing data-preprocessing bag-of-words

JamieCropley

5

answered Apr 27 at 13:19

1 vote

1 answer

52 views

How should I write the reward function to teach the agent the rules of this card game?

reinforcement-learning deep-rl reward-functions reward-design card-games

Neil Slater

23.2k

modified Apr 26 at 20:50

1 vote

1 answer

40 views

What happens if all the features are correlated with each other before clustering?

machine-learning unsupervised-learning clustering

Oliver Mason

5,027

answered May 5 at 11:18

3 votes

1 answer

40 views

What is the total number of actions and rewards count

reinforcement-learning deep-learning papers dqn datasets

Neil Slater

23.2k

modified May 14 at 12:51

1 vote

1 answer

47 views

Reinforcement learning algorithms for large problems that are not based on a neural network

reinforcement-learning algorithm-request state-of-the-art continuous-action-spaces continuous-state-spaces

nbro

33k

modified Apr 27 at 10:26

3 votes

1 answer

36 views

What should the discount factor for the non-slippery version of the FrozenLake environment be?

reinforcement-learning sutton-barto value-iteration discount-factor frozen-lake

Neil Slater

23.2k

modified 18 hours ago

2 votes

1 answer

45 views

Is it possible learning convergence is lost in Reinforcement Learning as the state space grows? What about catastrophic forgetting?

reinforcement-learning machine-learning q-learning sarsa

Diego Gomez

395

modified May 18 at 6:32

1 vote

1 answer

35 views

How to handled delayed rewards in contextual bandits [closed]

reinforcement-learning tensorflow experience-replay contextual-bandits

tjt

111

modified May 3 at 16:05

0 votes

1 answer

54 views

How can I reduce the loss? Why do I have the high loss and why do I have the gradient?

convolutional-neural-networks python image-recognition pytorch image-processing

JOGI

1

modified May 8 at 2:33

0 votes

1 answer

54 views

Why is depth-limited is preferable to minimax without depth limited

search minimax

Robin van Hoorn

104

answered May 3 at 16:18

1 vote

1 answer

42 views

Is there some kind of "weighted maximum" that allows the gradients to backpropagate? [closed]

neural-networks backpropagation

Tom Huntington

178

modified May 15 at 9:33

1 vote

1 answer

53 views

ML model to predict timeouts

classification algorithm-request model-request anomaly-detection forecasting

gwolter

11

modified May 3 at 13:45

2 votes

1 answer

32 views

What is a 'degenerate run' in evaluating model performance?

machine-learning terminology papers performance

Neil Slater

23.2k

answered May 7 at 20:18

2 votes

0 answers

52 views

How to reduce the dimensionality of the actions in RL

reinforcement-learning deep-rl action-spaces dimensionality-reduction

Leibniz

49

modified May 15 at 21:40

0 votes

1 answer

40 views

How to understand the GCN equation?

machine-learning deep-learning graph-neural-networks gnn

OmG

1,663

modified May 4 at 12:07

0 votes

1 answer

51 views

Pattern recognition for live stream Time serie

classification time-series pattern-recognition

Tiffany L

1

modified May 10 at 12:32

0 votes

1 answer

50 views

Is there a term for unquantifiably uncertain prior knowledge?

unsupervised-learning clustering

nbro

33k

answered May 16 at 9:21

1 vote

1 answer

38 views

Are there any guidelines on how to map the state space to integers in the case tabular RL algorithms?

reinforcement-learning reference-request implementation

Neil Slater

23.2k

modified May 2 at 19:02

1 vote

1 answer

29 views

Gradient bandit algorithm: is $\bar{R}_t$ average of all rewards or average of rewards corresponding to $A_t$?

reinforcement-learning sutton-barto multi-armed-bandits

Neil Slater

23.2k

modified Apr 30 at 19:22

1 vote

1 answer

36 views

Deep Features of Images - Better to use an unsupervised approach, or train a classifier with many classes?

deep-learning deep-neural-networks unsupervised-learning

Aray Karjauv

732

answered May 13 at 10:38

0 votes

1 answer

35 views

BERT2: How to use GPT2LMHeadModel to start a sentence, not complete it

natural-language-processing machine-translation natural-language-generation gpt-2

Raphael Lopez Kaufman

183

answered May 6 at 18:02

0 votes

1 answer

26 views

Is it possible to successively train an RL agent on the same environment with different data

reinforcement-learning

Raphael Lopez Kaufman

183

modified yesterday

0 votes

1 answer

33 views

Could Softmax Action Selection be useful to solve an episodic task with more than 100000 possible states and 2000 actions?

reinforcement-learning q-learning function-approximation episodic-tasks

Aquila

53

modified yesterday

0 votes

0 answers

42 views

Which algorithm can find the best combination of players to maximize the chance of getting a high score?

machine-learning terminology models algorithm-request

nbro

33k

modified Apr 27 at 10:28

0 votes

1 answer

32 views

How to manage impossible actions?

reinforcement-learning q-learning state-spaces action-spaces state-representations

Neil Slater

23.2k

modified yesterday

0 votes

0 answers

41 views

What is your training time of Resnet-18/Resnet-50 on Imagenet?

machine-learning training epochs image-net

nbro

33k

modified May 2 at 14:46

0 votes

0 answers

40 views

What is the correct partial derivative of $Y^c$ with respect to $A_{ij}^{kc}$?

deep-learning papers math derivative grad-cam++

Saurav Maheshkar

706

modified May 11 at 11:24

0 votes

1 answer

31 views

How is policy iteration capable of improving on a deterministic policy?

reinforcement-learning value-functions policy-iteration optimal-policy deterministic-policy

Neil Slater

23.2k

answered Apr 26 at 7:00

2 votes

1 answer

24 views

Can we also estimate $V_{\pi}$ with SARSA?

reinforcement-learning bellman-equations sarsa

Neil Slater

23.2k

modified 16 hours ago

1 vote

0 answers

39 views

Why do off-policy algorithms suffer from worse computational or time efficiency compared to on-policy algorithms?

reinforcement-learning off-policy-methods on-policy-methods computational-complexity sample-efficiency

kitaird

85

modified May 4 at 9:02

1 vote

0 answers

39 views

Learning values in open ball: which final layers to employ?

deep-learning objective-functions

Leonardo

111

modified Apr 30 at 19:47

1 vote

0 answers

38 views

Why does the SVM perform poorly on test data that has a different class distribution than the training data?

machine-learning overfitting support-vector-machine training-datasets test-datasets

Allie

11

modified May 11 at 8:28

1 vote

1 answer

38 views

Can you make a Neural Network drunk or high?

neural-networks reinforcement-learning human-like

Siarhei

11

answered yesterday

Top Questions

Looking for more? Browse the complete list of questions, or popular tags. Help us answer unanswered questions.