Artificial Intelligence Stack Exchange

2

votes

1

answer

10

views

What do the variables in the cross-correlation formula mean?

modified 9 mins ago nbro♦ 23.9k

2

votes

1

answer

56

views

not sure if fine-tuned network is finely-tuned

convolutional-neural-networks python training keras

modified 55 mins ago Community♦ 1

11

votes

6

answers

355

views

Are there any decentralized examples of AI systems with blockchain technology?

multi-agent-systems blockchain

answered 3 hours ago user1360448 63

2

votes

1

answer

45

views

A model for each sub-problem vs one model for the whole problem

machine-learning deep-learning ai-design computational-learning-theory

modified 3 hours ago Community♦ 1

3

votes

0

answers

32

views

How to train/update neural networks faster without a decrease in performance?

neural-networks machine-learning training efficiency

modified 3 hours ago Lerner Zhang 519

0

votes

0

answers

5

views

AI generator for imaginary street maps?

machine-learning comparison image-processing

asked 4 hours ago Chas Belov 1

1

vote

0

answers

10

views

How to build a test set for a model in industry?

testing test-datasets

asked 5 hours ago Lerner Zhang 519

1

vote

1

answer

66

views

Should batch-normalization/dropout/activation-function layers be used after the last fully connected layer?

neural-networks deep-learning architecture

modified 7 hours ago Community♦ 1

2

votes

1

answer

22

views

Are Genetic Algorithms suitable for problems like the Knuth problem?

genetic-algorithms evolutionary-algorithms genetic-programming norvig-russell

modified 9 hours ago nbro♦ 23.9k

1

vote

3

answers

101

views

How to improve neural network training against a large data set of points with varying magnitude

neural-networks tensorflow training optimization batch-normalization

modified 9 hours ago Community♦ 1

2

votes

1

answer

159

views

Have machine learning techniques been used to play outdoor games, like cricket or badminton?

machine-learning reference-request game-ai

modified 10 hours ago nbro♦ 23.9k

3

votes

1

answer

51

views

What is the pros and cons of increasing and decreasing the number of worker process in A3C?

reinforcement-learning deep-rl hyperparameter-optimization hyper-parameters a3c

modified 10 hours ago nbro♦ 23.9k

1

vote

1

answer

33

views

What dataset might Elon Musk's Dall-E have used?

natural-language-processing datasets generative-adversarial-networks image-generation natural-language-understanding

modified 10 hours ago Gavin 39

4

votes

2

answers

205

views

Variable Number of Inputs to Neural Networks

deep-learning image-recognition

modified 10 hours ago nbro♦ 23.9k

3

votes

1

answer

102

views

What AI technique should I use to assign a person to a task?

optimization constraint-satisfaction-problems planning linear-programming

modified 10 hours ago nbro♦ 23.9k

3

votes

1

answer

7k

views

What is an objective function?

terminology loss-functions optimization local-search meta-heuristics

modified 11 hours ago nbro♦ 23.9k

1

vote

1

answer

226

views

Are 1D CNNs really the appropriate model for human activity recognition?

convolutional-neural-networks recurrent-neural-networks long-short-term-memory human-activity-recognition

modified 11 hours ago nbro♦ 23.9k

0

votes

1

answer

45

views

When will we have computer programs that can compose mathematical proofs?

logic automated-theorem-proving automated-reasoning general-problem-solver

modified 11 hours ago nbro♦ 23.9k

1

vote

1

answer

91

views

How can I calculate the shortest path between two 2d vector points in an environment with obstacles?

search robotics a-star shortest-path-problem path-finding

modified 13 hours ago nbro♦ 23.9k

2

votes

1

answer

388

views

What are some simple open problems in multi-agent RL that would be suited for a bachelor's thesis?

reinforcement-learning reference-request research academia multi-objective-rl

modified 13 hours ago nbro♦ 23.9k

1

vote

1

answer

295

views

How does a PDDL solver find a solution for a given problem?

planning pddl

modified 13 hours ago nbro♦ 23.9k

-1

votes

0

answers

11

views

Is there a treatise that contains the following formulas? [closed]

reinforcement-learning alphazero

asked 14 hours ago ground clown 91

1

vote

0

answers

19

views

Where does this variation of the importance sampling weight come from?

reinforcement-learning dqn deep-rl experience-replay importance-sampling

modified 15 hours ago nbro♦ 23.9k

7

votes

2

answers

455

views

What is the difference between Q-learning, Deep Q-learning and Deep Q-network?

reinforcement-learning comparison q-learning dqn deep-rl

modified 16 hours ago nbro♦ 23.9k

-1

votes

0

answers

14

views

What is the difference between a network framework and an architechture? [closed]

neural-networks terminology architecture

asked 16 hours ago Bert Gayus 31

3

votes

0

answers

29

views

Does DQN generalise to unseen states in the case of discrete state-spaces?

reinforcement-learning dqn deep-rl generalization discrete-state-spaces

modified 16 hours ago nbro♦ 23.9k

3

votes

0

answers

21

views

Is non-negative matrix factorization for machine learning obsolete?

neural-networks machine-learning reference-request applications

modified 16 hours ago nbro♦ 23.9k

1

vote

1

answer

69

views

Reinforcement learning with industrial continuous process

reinforcement-learning supervised-learning

modified 16 hours ago Community♦ 1

3

votes

2

answers

146

views

What is the difference between return and expected return?

reinforcement-learning comparison q-learning return expectation

modified 16 hours ago nbro♦ 23.9k

0

votes

0

answers

20

views

Is the dimensionality of the query and key tensors in this implementation of the transformer's self-attention correct?

neural-networks tensorflow transformer implementation attention

modified 17 hours ago nbro♦ 23.9k

3

votes

1

answer

77

views

Does a converging (deep) neural network exist for every possible training data?

neural-networks

modified 19 hours ago John Doe 133

7

votes

2

answers

151

views

Why state-action value function as an expected value of the return and state value function, does not need to follow policy?

reinforcement-learning bellman-equations

modified 20 hours ago David Ireland 2,882

2

votes

1

answer

73

views

What method to identify markers in data series via machine learning

pattern-recognition time-series

modified 20 hours ago Community♦ 1

1

vote

0

answers

13

views

CSP heuristic to simultaneously reduce conflicts and find near optimal assignment

heuristics constraint-satisfaction-problems local-search

modified 21 hours ago nbro♦ 23.9k

2

votes

1

answer

127

views

How can neural networks approximate any continuous function but have $\mathcal{VC}$ dimension only proportional to their number of parameters?

comparison computational-learning-theory vc-dimension universal-approximation-theorems

modified 21 hours ago nbro♦ 23.9k

7

votes

3

answers

1k

views

What is the difference between hypothesis space and representational capacity?

machine-learning terminology computational-learning-theory hypothesis-class capacity

modified 21 hours ago nbro♦ 23.9k

4

votes

2

answers

334

views

How to estimate the capacity of a neural network?

neural-networks deep-learning computational-learning-theory vc-dimension capacity

modified 21 hours ago nbro♦ 23.9k

1

vote

0

answers

24

views

Gradient Based Inverse Reinforcement Learning

reinforcement-learning gradient-descent inverse-rl

modified 21 hours ago ИванКарамазов 11

9

votes

3

answers

356

views

Are there any rules of thumb for having some idea of what capacity a neural network needs to have for a given problem?

neural-networks computational-learning-theory regularization vc-dimension capacity

modified 22 hours ago nbro♦ 23.9k

1

vote

1

answer

94

views

Is the VC Dimension meaningful in the context of Reinforcement Learning?

machine-learning reinforcement-learning computational-learning-theory vc-dimension vc-theory

modified 22 hours ago nbro♦ 23.9k

1

vote

1

answer

70

views

If a neural network is a universal function approximator, can it have any prior beliefs?

neural-networks computational-learning-theory universal-approximation-theorems vc-theory no-free-lunch-theorems

modified 22 hours ago DuttaA 5,123

1

vote

0

answers

11

views

For binary classification learning problems, how should I label instances where I'm only 60% sure?

neural-networks classification data-labelling

asked 22 hours ago Alexander Soare 945

15

votes

3

answers

4k

views

Where can I find the proof of the universal approximation theorem?

neural-networks reference-request proofs function-approximation universal-approximation-theorems

modified 22 hours ago AIM_BLB 475

2

votes

1

answer

35

views

What does the notation $[m]=\{1, \ldots, m\}$ mean in the equation of the empirical error?

machine-learning computational-learning-theory notation books

modified 22 hours ago nbro♦ 23.9k

3

votes

0

answers

84

views

Can one agent command another agent in a multi-agent reinforcement learning setting? [closed]

reinforcement-learning intelligent-agent multi-agent-systems hierarchical-rl

modified 22 hours ago Community♦ 1

1

vote

0

answers

13

views

Is it possible to ensure the convergence when training a RNN weight on its SVD decomposition?

neural-networks recurrent-neural-networks papers gradient-descent optimization

asked 23 hours ago Minh Khôi 111

53

votes

11

answers

9k

views

What are some well-known problems where neural networks don't do very well?

neural-networks deep-learning reference-request applications

modified 23 hours ago nbro♦ 23.9k

10

votes

2

answers

573

views

What are the learning limitations of neural networks trained with backpropagation?

neural-networks machine-learning backpropagation universal-approximation-theorems computational-learning-theory

modified 23 hours ago nbro♦ 23.9k

Top Questions

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