respectful's user avatar
respectful's user avatar
respectful's user avatar
respectful
  • Member for 3 years, 1 month
  • Last seen more than a week ago
35 votes
6 answers
10k views

Why do CNN's sometimes make highly confident mistakes, and how can one combat this problem?

10 votes
1 answer
559 views

How does the forget layer of an LSTM work?

10 votes
3 answers
4k views

Can we get the inverse of the function that a neural network represents?

7 votes
2 answers
1k views

Where to publish a first article in Deep Reinforcement Learning?

4 votes
1 answer
624 views

Any explanation why multiple linear layers work better than a single linear layer in practice?

  • 141
4 votes
1 answer
145 views

What activation functions are currently popular?

  • 242
3 votes
1 answer
105 views

Are there any agents that are based on quantum computing?

3 votes
0 answers
88 views

Why do regression LSTMs learn high to low inputs significantly better than low to high?

  • 1,266
2 votes
1 answer
103 views

How does the weight update formula for logistic regression work?

  • 31
2 votes
1 answer
420 views

What are some online courses on artificial general intelligence?

  • 35k
2 votes
0 answers
39 views

Is there a theory that captures the following ideas?

  • 131
2 votes
1 answer
96 views

Why does an LSTM cycle on initialisation?

  • 1,266
2 votes
1 answer
150 views

If $h_1(n)$ is admissible, why does A* tree search with $h_2(n) = 3h_1(n)$ return a path that is at most thrice as long as the optimal path?

2 votes
1 answer
870 views

If $h_i$ are consistent and admissible, are their sum, maximum, minimum and average also consistent and admissible?

2 votes
1 answer
111 views

Is there an error in A* optimality proof Russel-Norvig 4th edition?

  • 71
0 votes
0 answers
134 views

Comparing heuristics in A* search and rescue operation