User nbro

95 votes

3 answers

85k views

What is self-supervised learning in machine learning?

asked Feb 16, 2019 at 20:02

38 votes

5 answers

18k views

What is the difference between latent and embedding spaces?

asked Mar 17, 2019 at 11:56

28 votes

1 answer

15k views

What is the Bellman operator in reinforcement learning?

asked Mar 6, 2019 at 14:07

28 votes

1 answer

23k views

What is the credit assignment problem?

asked Jun 18, 2019 at 0:35

24 votes

5 answers

20k views

What is non-Euclidean data?

asked Mar 14, 2019 at 10:20

22 votes

3 answers

5k views

Why doesn't Q-learning converge when using function approximation?

asked Apr 5, 2019 at 18:23

18 votes

3 answers

3k views

Which explainable artificial intelligence techniques are there?

asked Jun 15, 2019 at 23:07

18 votes

3 answers

5k views

What is geometric deep learning?

asked Mar 12, 2019 at 10:29

16 votes

3 answers

4k views

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

asked Feb 15, 2019 at 13:20

14 votes

3 answers

6k views

Why exactly do neural networks require i.i.d. data?

asked Feb 23, 2019 at 13:30

14 votes

1 answer

8k views

What is the relation between online (or offline) learning and on-policy (or off-policy) algorithms?

asked Feb 9, 2019 at 14:48

13 votes

3 answers

938 views

Why teaching only search algorithms in a short introductory AI course?

asked Dec 20, 2016 at 15:44

12 votes

1 answer

13k views

How can the convolution operation be implemented as a matrix multiplication?

asked Mar 12, 2019 at 13:57

12 votes

4 answers

3k views

What are the purposes of autoencoders?

asked Mar 23, 2019 at 15:53

8 votes

1 answer

2k views

Which machine learning models are universal function approximators?

asked May 10, 2019 at 12:15

8 votes

3 answers

16k views

What is the difference between a stochastic and a deterministic policy?

asked May 12, 2019 at 18:50

8 votes

1 answer

7k views

What is the difference between a stationary and a non-stationary policy?

asked Jun 27, 2019 at 15:14

7 votes

1 answer

3k views

Why does a negative reward for every step really encourage the agent to reach the goal as quickly as possible?

asked Nov 1, 2020 at 23:09

6 votes

1 answer

1k views

What is the return-to-go in reinforcement learning?

asked Oct 10, 2020 at 15:43

6 votes

2 answers

1k views

How are the reward functions $R(s)$, $R(s, a)$ and $R(s, a, s')$ equivalent?

asked Feb 7, 2019 at 15:38

6 votes

1 answer

548 views

What is the relation between a policy which is the solution to a MDP and a policy like $\epsilon$-greedy?

asked Feb 10, 2019 at 16:34

5 votes

1 answer

2k views

What is a graph neural network?

asked Mar 12, 2019 at 10:46

5 votes

1 answer

6k views

How can we use linear programming to solve an MDP?

asked Mar 14, 2019 at 21:12

5 votes

1 answer

117 views

Why should we study causation in artificial intelligence?

asked Mar 22, 2019 at 15:11

5 votes

1 answer

2k views

Which paper introduced the term "softmax"?

asked Jul 10, 2020 at 0:37

4 votes

1 answer

6k views

What are bag-of-features in computer vision?

asked Jun 15, 2020 at 19:24

4 votes

2 answers

2k views

Do convolutional neural networks perform convolution or cross-correlation?

asked Jun 18, 2020 at 17:13

4 votes

1 answer

439 views

Why do we have two similar action selection strategies for UCB1?

asked Oct 23, 2020 at 10:32

4 votes

1 answer

394 views

How are afterstate value functions mathematically defined?

asked Nov 23, 2020 at 13:48

4 votes

1 answer

645 views

Is there any difference between a control and an action in reinforcement learning?

asked Jun 28, 2019 at 17:54

Stack Exchange Network

58 Questions

What is self-supervised learning in machine learning?

What is the difference between latent and embedding spaces?

What is the Bellman operator in reinforcement learning?

What is the credit assignment problem?

What is non-Euclidean data?

Why doesn't Q-learning converge when using function approximation?

Which explainable artificial intelligence techniques are there?

What is geometric deep learning?

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

Why exactly do neural networks require i.i.d. data?

What is the relation between online (or offline) learning and on-policy (or off-policy) algorithms?

Why teaching only search algorithms in a short introductory AI course?

How can the convolution operation be implemented as a matrix multiplication?

What are the purposes of autoencoders?

Which machine learning models are universal function approximators?

What is the difference between a stochastic and a deterministic policy?

What is the difference between a stationary and a non-stationary policy?

Why does a negative reward for every step really encourage the agent to reach the goal as quickly as possible?

What is the return-to-go in reinforcement learning?

How are the reward functions $R(s)$, $R(s, a)$ and $R(s, a, s')$ equivalent?

What is the relation between a policy which is the solution to a MDP and a policy like $\epsilon$-greedy?

What is a graph neural network?

How can we use linear programming to solve an MDP?

Why should we study causation in artificial intelligence?

Which paper introduced the term "softmax"?

What are bag-of-features in computer vision?

Do convolutional neural networks perform convolution or cross-correlation?

Why do we have two similar action selection strategies for UCB1?

How are afterstate value functions mathematically defined?

Is there any difference between a control and an action in reinforcement learning?