Hottest Questions Today

0

votes

1

answer

21

views

How to identify the areas to reduce over fitting?

answered 52 mins ago naive 121

1

vote

1

answer

20

views

Where can we use the Bayes' theorem in artificial intelligence?

applications bayes-theorem

modified 14 hours ago nbro 2,440

2

votes

0

answers

27

views

Intuition behind $\gamma$-discounted state frequency

reinforcement-learning

modified 2 hours ago Sherwin Chen 165

0

votes

1

answer

28

views

What does the formula $1-\sum_i(e_i-a_i)^2$ mean in this NEAT Python API?

ai-basics math neat notation

answered 9 hours ago guest 1

0

votes

0

answers

20

views

A few questions regarding the on-policy $\epsilon$-greedy Monte Carlo control algorithm [on hold]

reinforcement-learning rl-an-introduction monte-carlo

modified 18 hours ago nbro 2,440

0

votes

1

answer

29

views

Monte-Carlo, every-visit gridworld, exploring starts, python code gets stuck in foreverloop in episode generation

python monte-carlo

modified 22 hours ago Late347 9

1

vote

1

answer

15

views

Is it mostly the case to train with available models

training models

answered yesterday malioboro 704

3

votes

1

answer

32

views

Variational Autoencoder task for better feature extraction

neural-networks convolutional-neural-networks unsupervised-learning autoencoders supervised-learning

modified 18 hours ago DuttaA 2,505

2

votes

1

answer

39

views

Maximum Q value for new state in Q-Learning never exists

q-learning

answered yesterday Neil Slater 6,504

0

votes

0

answers

13

views

Detecting playing cards with a neural network

image-recognition classification getting-started

modified yesterday Philip Raeisghasem 1,125

0

votes

0

answers

14

views

How to manage 'action churn rates' in multi-agent systems?

multi-agent-systems planning

modified yesterday Philip Raeisghasem 1,125

0

votes

0

answers

13

views

Using neuroevolution to train a 7 DOF arm: How do I choose the correct fitness function and hyperparameters?

evolutionary-algorithms neat artificial-neuron robotics

asked yesterday NetHacker 131

1

vote

1

answer

23

views

how to benefit from previous training weights in training again to increase accuracy?

convolutional-neural-networks training keras

modified 2 days ago malioboro 704

2

votes

1

answer

46

views

Why is dot product attention faster than additive attention?

neural-networks machine-learning deep-learning attention

answered 2 days ago John Doucette 3,465

7

votes

1

answer

79

views

Are there reinforcement learning algorithms that scale to large problems?

reinforcement-learning

modified yesterday Philip Raeisghasem 1,125

2

votes

2

answers

39

views

Do we have cross-language vector space for word embedding?

natural-language-processing word-embedding

answered yesterday HLeb 16

1

vote

1

answer

40

views

How can we create a vector space where word spelling and pronunciation can be easily compared?

natural-language-processing word-embedding

modified yesterday Jaume Oliver Lafont 111

4

votes

1

answer

197

views

What loss function to use when labels are probabilities?

neural-networks machine-learning loss-functions probability-distribution

modified Apr 15 at 10:11 nbro 2,440

0

votes

2

answers

37

views

How can the A* algorithm be optimized?

algorithm optimization search a-star

modified Apr 16 at 15:33 nbro 2,440

2

votes

1

answer

36

views

+50

How important is it that the generator of a generative adversarial network doesn't take in information about input classes?

keras generative-model generative-adversarial-networks

modified yesterday Novak 121

1

vote

1

answer

32

views

Why is informed search more efficient than uniformed search?

ai-basics search difference efficiency relation

modified Apr 16 at 14:05 nbro 2,440

2

votes

1

answer

48

views

How do I choose the number of neurons in the fully-connected layer before the softmax layer?

neural-networks deep-learning convolutional-neural-networks ai-design

modified Apr 16 at 9:33 nbro 2,440

3

votes

0

answers

40

views

What are stable ways of doing online machine learning?

neural-networks machine-learning incremental-learning online-learning

modified Apr 16 at 10:01 nbro 2,440

0

votes

0

answers

52

views

neural net editing neural net and evolution

neural-networks theory reference-request evolutionary-game-theory

modified Apr 16 at 3:46 Dimer 24

3

votes

1

answer

70

views

What is the difference between search and learning?

deep-learning philosophy search

modified Apr 14 at 22:58 John Doucette 3,465

0

votes

0

answers

26

views

E.T.P. Je sais CAM381A2LCM [on hold]

algorithm

asked Apr 15 at 20:07 Red_Rose 1

1

vote

1

answer

48

views

Meaning of the statement $\forall x \exists y \forall z (z \neq y \iff f(x) \neq z)$

ai-basics logic

answered Apr 14 at 19:57 Philip Raeisghasem 1,125

0

votes

0

answers

17

views

Turn a NES ROM into object/tile representation

deep-learning reinforcement-learning neat open-ai

asked Apr 16 at 2:10 niallmandal 33

3

votes

1

answer

24

views

Are successive actions independent?

reinforcement-learning markov-decision-process importance-sampling

modified Apr 15 at 20:12 John Doucette 3,465

0

votes

0

answers

21

views

How do I create syntactically correct sentences given several words?

machine-learning natural-language-processing

modified Apr 15 at 9:45 nbro 2,440

1

vote

1

answer

19

views

Can AI help summarize article or abstract sentence keyword?

natural-language-processing artificial-neuron

answered Apr 15 at 8:29 Oliver Mason 1,211

-1

votes

0

answers

41

views

Can differential equations be replaced by a neural networks?

neural-networks math

asked Apr 14 at 7:05 Manuel Rodriguez 1,264

1

vote

1

answer

49

views

How can the $\lambda$-return be defined recursively?

reinforcement-learning rl-an-introduction return eligibility-traces

modified Apr 14 at 7:44 Philip Raeisghasem 1,125

3

votes

1

answer

28

views

What are possible functions assigned on decision nodes for decision tree prediction?

decision-tree

answered Apr 15 at 0:58 Frans Rodenburg 126

2

votes

1

answer

31

views

Why is image recognition a key function of AI?

image-recognition philosophy artificial-life

answered Apr 14 at 14:50 Oliver Mason 1,211

3

votes

0

answers

33

views

Understanding notation of Goodfellow's GAN objective function

machine-learning generative-model generative-adversarial-networks notation

modified Apr 15 at 9:58 nbro 2,440

0

votes

1

answer

75

views

Bachelor thesis in reinforcement learning

reinforcement-learning open-ai academia

modified Apr 13 at 20:45 John Doucette 3,465

1

vote

1

answer

45

views

Can I use neural networks for a problem (in description)?

neural-networks

answered Apr 15 at 2:08 Frans Rodenburg 126

3

votes

1

answer

37

views

How can alpha zero learn if the tree search stops and restarts before finishing a game?

deep-learning reinforcement-learning monte-carlo-tree-search alphazero

modified Apr 12 at 19:07 Philip Raeisghasem 1,125

4

votes

1

answer

59

views

Is it possible to make a 'forked path' neural network?

neural-networks machine-learning convolutional-neural-networks image-recognition

modified Apr 11 at 5:17 Sooryakiran Pallikulathil 76

1

vote

0

answers

30

views

Difficulty understanding Monte Carlo policy evaluation (state-value) for gridworld

reinforcement-learning monte-carlo

asked Apr 12 at 17:06 Late347 9

1

vote

0

answers

13

views

Deciding the rewards for different actions in Pong for a DQN agent

reinforcement-learning dqn rewards reward-clipping

asked Apr 13 at 16:57 RyanD96 6

1

vote

0

answers

41

views

ChatBot applications [Academia]

natural-language-processing ai-basics chat-bots knowledge-representation reference-request

modified Apr 11 at 21:04 DukeZhou♦ 4,107

3

votes

1

answer

38

views

Why are not validation accuracy and loss as smooth as train accuracy and loss?

neural-networks convolutional-neural-networks training

modified Apr 10 at 17:57 DuttaA 2,505

2

votes

1

answer

31

views

Confused about group convolution

convolutional-neural-networks

answered Apr 12 at 0:58 j314erre 111

4

votes

2

answers

96

views

Which loss function is the brain optimizing in order to learn advanced visual skills without expert/human supervision?

machine-learning computer-vision cognitive-science biology

modified Apr 11 at 21:03 Pablo Messina 47

0

votes

1

answer

21

views

How do map providers like Google calculate the distance between two coordinates and find turn by turn directions?

reinforcement-learning object-recognition

modified Apr 12 at 10:14 Oliver Mason 1,211

1

vote

0

answers

19

views

What is the best method to deal with heterogeneous multi agent system MAS?

deep-learning multi-agent-systems

asked Apr 12 at 13:38 i_th 116

Top Questions

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