user avatar
user avatar
user avatar
volperossa
  • Member for 7 years, 11 months
  • Last seen more than a week ago
7 votes
1 answer
5k views

gradient descent and local maximum

5 votes
2 answers
837 views

Why does pre-training help avoid the vanishing gradient problem?

5 votes
2 answers
655 views

SciKit Learn: Multilayer perceptron early stopping, restore best weights

4 votes
1 answer
6k views

cross entropy loss max value

4 votes
2 answers
948 views

conjugate prior: is ever the best choice?

3 votes
1 answer
108 views

Expectation Maximization EM: is possibile in every case?

3 votes
1 answer
243 views

Definition of Bayesian network

3 votes
1 answer
197 views

Boltzmann machines: learning algorithm

3 votes
1 answer
206 views

Differential Privacy: why $\delta$ negligible on the row numbers?

3 votes
0 answers
100 views

ICA: a question about the non-gaussian requirement

3 votes
1 answer
427 views

Why do DeconvNet use ReLU in the backward pass?

2 votes
0 answers
178 views

boltzmann machine; from logistic function to boltzmann distribution

1 vote
1 answer
88 views

simply demostration on conditioned probability

1 vote
0 answers
40 views

sampling: question about variance estimation

1 vote
1 answer
578 views

correlation and independence: common mistake?

1 vote
1 answer
163 views

logistic regression - why we forget assumption on data?

1 vote
0 answers
20 views

reproducing kernel hilbert space notation

1 vote
1 answer
58 views

automatic diffentiation (autograd): when the explicit definition of the gradient function is needed?

0 votes
0 answers
1k views

Expectation Maximization (EM) stopping criterion