stoic-santiago's user avatar
stoic-santiago's user avatar
stoic-santiago's user avatar
stoic-santiago
  • Member for 4 years
  • Last seen more than a month ago
7 votes
2 answers
4k views

Aren't all discrete convolutions (not just 2D) linear transforms?

7 votes
1 answer
2k views

Why do we update all layers simultaneously while training a neural network?

6 votes
1 answer
161 views

What does the number of required expert demonstrations in Imitation Learning depend on?

6 votes
1 answer
3k views

What are the pros and cons of sparse and dense rewards in reinforcement learning?

5 votes
1 answer
907 views

What's the optimal policy in the rock-paper-scissors game?

5 votes
1 answer
498 views

Why does TD Learning require Markovian domains?

4 votes
1 answer
1k views

When do SARSA and Q-Learning converge to optimal Q values?

4 votes
1 answer
447 views

Why are state-values alone not sufficient in determining a policy (without a model)?

4 votes
1 answer
198 views

Why does REINFORCE work at all?

4 votes
2 answers
750 views

Why is regret so defined in MABs?

4 votes
2 answers
727 views

What is the effect of using pooling layers in CNNs?

4 votes
0 answers
476 views

How does SGD escape local minima?

4 votes
1 answer
152 views

Why does L1 regularization yield sparse features?

3 votes
2 answers
4k views

What's the difference between estimation and approximation error?

3 votes
0 answers
32 views

What is meant by subspace clustering in MFA?

3 votes
2 answers
264 views

Why does (not) the distribution of states depend on the policy parameters that induce it?

2 votes
1 answer
261 views

What is the surrogate loss function in imitation learning, and how is it different from the true cost?

2 votes
1 answer
67 views

Is there an equivalent model to the Hidden Markov Model for continuous hidden variables?

2 votes
0 answers
717 views

What's the nearest neighbor algorithm used for upsampling?

2 votes
0 answers
54 views

What are some other real-life examples of simple policies but complex value functions?

2 votes
2 answers
3k views

Why are decision trees and random forests scale invariant?

2 votes
0 answers
80 views

Why is 'scatter' used instead of variance in LDA?

2 votes
1 answer
71 views

How exactly does nested cross-validation work?

2 votes
1 answer
184 views

Why can't pure KG embedding methods discover multi-hop relations paths?

2 votes
3 answers
601 views

Why does it make sense to study MDPs with finite state and action spaces?

2 votes
0 answers
97 views

How are the classical MDP and the object-oriented MDP views different?

2 votes
1 answer
1k views

What is the KWIK framework?

2 votes
2 answers
140 views

How can Siamese Networks be viewed as RNNs?

2 votes
0 answers
17 views

How do multiple coordinate systems help in capturing invariant features?

1 vote
1 answer
51 views

Why is this variable in equation 2 of the SQAIR paper a random vector of $n$ ones followed by a zero?