Hottest Questions Today

2

votes

0

answers

14

views

Expected SARSA vs SARSA in “RL: An Introduction”

modified 6 hours ago nbro 1,292

1

vote

1

answer

13

views

How do I avoid an agent to tend to terminate in a negative state when time needs to be taken into account?

reinforcement-learning rewards

answered 6 hours ago Jaden Travnik♦ 2,623

1

vote

1

answer

19

views

Is the definition of machine learning by Mitchell in his book “Machine Learning” valid?

machine-learning ai-basics terminology definitions

modified 1 hour ago DukeZhou♦ 3,777

2

votes

1

answer

22

views

How is equation 8 derived in the paper “Self-critical sequence training for image captioning”?

neural-networks reinforcement-learning loss-functions papers reinforce

modified 12 hours ago rubencart 11

0

votes

1

answer

14

views

Face liveness detection using face landmark points

machine-learning

answered 12 hours ago Xpector 11

0

votes

1

answer

19

views

Training a neural network to output the conditional probability of an event when the training data output is only binary

neural-networks

modified 14 hours ago Karl 1

1

vote

2

answers

24

views

Relative Importance of Input Features

neural-networks deep-learning

answered 15 hours ago ssegvic 259

0

votes

1

answer

18

views

Loss function spikes

neural-networks keras loss-functions

answered 12 hours ago ssegvic 259

2

votes

0

answers

16

views

How to handle varying length of inputs that represent dependencies and recursivity in deep neural networks in case of regression?

neural-networks deep-network

modified yesterday Emma 111

2

votes

1

answer

24

views

Is 7. of the UK Gov Al healthcare code of conduct possible?

ethics healthcare

answered 16 hours ago Manuel Rodriguez 1,396

1

vote

0

answers

16

views

What is the difference between a non-stationary policy and a state that stores time?

reinforcement-learning policy

modified yesterday nbro 1,292

1

vote

2

answers

31

views

Modelling gut-feeling/subconscious knowledge of stock market traders

neural-networks machine-learning reinforcement-learning

answered 15 hours ago Xpector 11

1

vote

1

answer

30

views

How do I apply the value iteration algorithm when there are two goal states?

reinforcement-learning rl-an-introduction value-iteration

modified yesterday nbro 1,292

0

votes

1

answer

15

views

Loss/accuracy on Synthetic data

data-science

modified yesterday Anders Ellern Bilgrau 103

1

vote

0

answers

18

views

Why is the learning rate is already very small (1e-05) while the model convergences too fast?

machine-learning deep-learning computer-vision

asked yesterday dwqy11 6

2

votes

1

answer

31

views

Why does Deep Q Network outputs multiple Q values?

reinforcement-learning q-learning deep-rl

modified yesterday nbro 1,292

2

votes

2

answers

66

views

Is Windows a bad choice for DRL?

reinforcement-learning software-evaluation

modified 2 days ago DukeZhou♦ 3,777

3

votes

0

answers

19

views

Symbolic “math” using trained networks

neural-networks

asked 2 days ago Steven Sagona 156

2

votes

2

answers

75

views

What is self-supervision in machine learning?

machine-learning supervised-learning self-supervised-learning

modified 9 hours ago nbro 1,292

1

vote

2

answers

81

views

Is there more than one Q-matrix update formula?

reinforcement-learning python q-learning

modified Feb 18 at 20:46 Dennis Soemers 3,797

1

vote

1

answer

46

views

Is it possible to use a trained neural network to predict a feature, given other features and output?

matlab deep-learning

answered 2 days ago Joyjit Chatterjee 18

1

vote

0

answers

38

views

Why is gradient ascent necessary when training Actor Critic agents?

reinforcement-learning actor-critic

modified yesterday Emma 111

4

votes

1

answer

46

views

Is fuzzy logic connected to neural networks?

neural-networks fuzzy-logic

modified 2 days ago Oliver Mason 1,068

2

votes

2

answers

88

views

Can we define the AI singularity mathematically?

math learning-algorithms singularity

modified 2 days ago Phylliida 127

2

votes

0

answers

18

views

Choosing more than one action in a parameterized policy

reinforcement-learning policy-iteration

modified yesterday nbro 1,292

1

vote

2

answers

61

views

RL vs Supervised Learning vs Planning

machine-learning reinforcement-learning planning

modified yesterday SeeDerekEngineer 118

0

votes

2

answers

28

views

Do I need an encoder-decoder architecture to predict the next item of a sequence?

deep-learning natural-language-processing recurrent-neural-networks machine-translation

modified 15 hours ago nbro 1,292

0

votes

0

answers

18

views

What are the prerequisites and skills for studying machine learning? [on hold]

machine-learning artificial-consciousness

modified 2 days ago nbro 1,292

0

votes

0

answers

12

views

Using a combination of gradient boosting with LSTM for classification? [migrated]

deep-learning lstm

asked 2 days ago Joyjit Chatterjee 18

1

vote

2

answers

66

views

Find object location (x, y) in an image

neural-networks machine-learning computer-vision object-recognition

answered Feb 18 at 22:45 malioboro 458

1

vote

2

answers

34

views

To what does the number of hidden layers in a neural network correspond?

neural-networks models hidden-layers

answered Feb 18 at 22:40 Nyos 31

1

vote

1

answer

30

views

Robot Arm Deep Q Learning Actions

deep-learning reinforcement-learning q-learning robotics

answered Feb 18 at 17:12 Jaden Travnik♦ 2,623

0

votes

0

answers

12

views

What is the right way to convolve over word embeddings?

convolutional-neural-networks natural-language-processing knowledge-representation wordvector

asked 2 days ago user3352632 151

5

votes

4

answers

542

views

Is the optimal policy always stochastic if the environment is also stochastic?

reinforcement-learning stochastic-policy deterministic-policy policy environment

answered Feb 16 at 2:37 ron dembo 1

0

votes

0

answers

36

views

How to solve constraint satisfaction problem of two queen and two knights on a 4x4 grid

ai-basics

modified 2 days ago DukeZhou♦ 3,777

3

votes

1

answer

45

views

Should I model my problem as a semi-MDP?

reinforcement-learning markov-decision-process semi-mdp hierarchical-rl

modified Feb 18 at 18:11 nbro 1,292

1

vote

0

answers

15

views

Is policy learning and online system identification the same?

control-problem

modified Feb 18 at 18:56 Manuel Rodriguez 1,396

3

votes

0

answers

18

views

What are the main benefits of using Bayesian networks?

math bayes bayesian-network

modified Feb 18 at 17:07 nbro 1,292

1

vote

2

answers

84

views

How is it that AI can become biased, and what are the proposals to mitigate this?

modified Feb 17 at 21:50 Nyos 31

1

vote

2

answers

45

views

Difference between Graph Search and Tree Search

search breadth-first-search

answered Feb 17 at 18:34 sabeen kanwal 11

1

vote

0

answers

27

views

Is a very powerful oracle sufficient to trigger the AI singularity?

algorithm optimization singularity

modified Feb 17 at 23:06 Phylliida 127

0

votes

0

answers

50

views

Using AI to guess a mathematical pattern of certain polynomials in four variables: practical challenge

neural-networks machine-learning deep-learning python implementation

modified Feb 18 at 16:01 jj_p 101

2

votes

1

answer

29

views

Mnist CNN Architecture

convolutional-neural-networks image-recognition pytorch

answered Feb 17 at 17:07 JahKnows 435

0

votes

0

answers

26

views

How do you implement NEAT by taking into account the loops?

neat

modified Feb 17 at 20:57 nbro 1,292

1

vote

0

answers

30

views

How do I write a genetic algorithm to solve the knapsack problem?

genetic-algorithms java

modified yesterday nbro 1,292

0

votes

0

answers

25

views

How to approach the sequential decision-making problem with sub-actions with RL?

reinforcement-learning combinatorial-games

modified Feb 18 at 17:59 malioboro 458

1

vote

0

answers

16

views

Complex systems constituting an entity unto itself

modified Feb 18 at 12:56 drabsv 106

1

vote

1

answer

43

views

How does backpropagation with unbounded activation functions such as ReLU work?

neural-networks backpropagation relu

modified Feb 16 at 15:06 ssegvic 259

Top Questions

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