User nbro

94 votes

Accepted

What is self-supervised learning in machine learning?

answered Feb 16, 2019 at 20:02

70 votes

Accepted

Are neural networks prone to catastrophic forgetting?

answered Jul 10, 2019 at 10:14

47 votes

Why does ChatGPT fail in playing "20 questions"?

answered May 24 at 14:45

35 votes

Accepted

What is the credit assignment problem?

answered Jun 18, 2019 at 0:35

33 votes

How can an AI train itself if no one is telling it if its answer is correct or wrong?

answered Nov 24, 2019 at 15:24

32 votes

Is a switch from R to Python worth it?

answered Aug 4, 2019 at 23:16

30 votes

Accepted

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

answered Jul 11, 2019 at 9:05

28 votes

Accepted

Is there any research on the development of attacks against artificial intelligence systems?

answered Oct 9, 2019 at 21:56

25 votes

Accepted

How is BERT different from the original transformer architecture?

answered Sep 21, 2020 at 16:04

24 votes

Accepted

What is a fully convolution network?

answered Jun 12, 2020 at 13:25

24 votes

What's the difference between model-free and model-based reinforcement learning?

answered Nov 7, 2018 at 11:35

23 votes

Accepted

What is the difference between First-Visit Monte-Carlo and Every-Visit Monte-Carlo Policy Evaluation?

answered Feb 22, 2019 at 14:45

21 votes

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

answered Mar 11, 2020 at 18:20

18 votes

Why do most deep learning papers not include an implementation?

answered May 14, 2020 at 14:44

18 votes

Accepted

Why do we need common sense in AI?

answered Jul 8, 2019 at 14:41

16 votes

Accepted

What are the differences between Q-Learning and A*?

answered Aug 17, 2020 at 0:26

16 votes

What are examples of promising AI/ML techniques that are computationally intractable?

answered Oct 21, 2019 at 0:15

15 votes

How does one prove comprehension in machines?

answered Jun 3, 2020 at 2:45

15 votes

Accepted

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

answered May 12, 2019 at 18:50

14 votes

Accepted

What is the difference between active learning and online learning?

answered Aug 24, 2020 at 20:44

14 votes

Should neural nets be deeper the more complex the learning problem is?

answered Apr 27, 2020 at 15:33

14 votes

Accepted

What sort of mathematical problems are there in AI that people are working on?

answered Jun 21, 2019 at 14:48

14 votes

Accepted

Problems that only humans will ever be able to solve

answered May 5, 2019 at 13:06

14 votes

What are examples of promising AI/ML techniques that are computationally intractable?

answered Oct 20, 2019 at 21:24

13 votes

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

answered Jan 22, 2021 at 12:45

13 votes

Accepted

Can supervised learning be recast as reinforcement learning problem?

answered Aug 27, 2019 at 23:14

13 votes

Accepted

What are the differences between A* and greedy best-first search?

answered Nov 10, 2018 at 13:32

13 votes

Accepted

What algorithms are considered reinforcement learning algorithms?

answered Apr 30, 2019 at 14:54

13 votes

Accepted

Which tasks are called as downstream tasks?

answered Jun 27, 2021 at 15:07

12 votes

Accepted

Can reinforcement learning be used for tasks where only one final reward is received?

answered May 7, 2019 at 15:59

Stack Exchange Network

780 Answers

What is self-supervised learning in machine learning?

Are neural networks prone to catastrophic forgetting?

Why does ChatGPT fail in playing "20 questions"?

What is the credit assignment problem?

How can an AI train itself if no one is telling it if its answer is correct or wrong?

Is a switch from R to Python worth it?

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

Is there any research on the development of attacks against artificial intelligence systems?

How is BERT different from the original transformer architecture?

What is a fully convolution network?

What's the difference between model-free and model-based reinforcement learning?

What is the difference between First-Visit Monte-Carlo and Every-Visit Monte-Carlo Policy Evaluation?

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

Why do most deep learning papers not include an implementation?

Why do we need common sense in AI?

What are the differences between Q-Learning and A*?

What are examples of promising AI/ML techniques that are computationally intractable?

How does one prove comprehension in machines?

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

What is the difference between active learning and online learning?

Should neural nets be deeper the more complex the learning problem is?

What sort of mathematical problems are there in AI that people are working on?

Problems that only humans will ever be able to solve

What are examples of promising AI/ML techniques that are computationally intractable?

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

Can supervised learning be recast as reinforcement learning problem?

What are the differences between A* and greedy best-first search?

What algorithms are considered reinforcement learning algorithms?

Which tasks are called as downstream tasks?

Can reinforcement learning be used for tasks where only one final reward is received?