User volperossa

7 votes

1 answer

5k views

gradient descent and local maximum

asked Aug 13, 2018 at 11:58

5 votes

2 answers

686 views

SciKit Learn: Multilayer perceptron early stopping, restore best weights

neural-networks scikit-learn perceptron

asked Apr 14, 2020 at 10:36

5 votes

2 answers

847 views

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

neural-networks deep-learning backpropagation deep-belief-networks pre-training

asked Jan 28, 2017 at 10:22

4 votes

2 answers

958 views

conjugate prior: is ever the best choice?

bayesian maximum-likelihood prior hyperparameter conjugate-prior

asked Apr 16, 2017 at 9:04

4 votes

1 answer

6k views

cross entropy loss max value

loss-functions extreme-value cross-entropy

asked Feb 15, 2019 at 13:53

3 votes

0 answers

103 views

ICA: a question about the non-gaussian requirement

normal-distribution central-limit-theorem signal-processing independent-component-analysis

asked Dec 8, 2020 at 11:32

3 votes

1 answer

110 views

Expectation Maximization EM: is possibile in every case?

maximum-likelihood random-variable likelihood expectation-maximization

asked Apr 19, 2017 at 11:15

3 votes

1 answer

210 views

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

differential-privacy

asked Mar 3, 2017 at 20:30

3 votes

1 answer

243 views

Definition of Bayesian network

probability bayesian conditional-probability graphical-model bayesian-network

asked Aug 23, 2014 at 1:38

3 votes

1 answer

199 views

Boltzmann machines: learning algorithm

machine-learning deep-learning restricted-boltzmann-machine deep-belief-networks generative-models

asked Jan 12, 2017 at 18:42

3 votes

1 answer

440 views

Why do DeconvNet use ReLU in the backward pass?

neural-networks conv-neural-network explanatory-models transposed-convolution

asked Mar 30, 2020 at 13:13

2 votes

0 answers

179 views

boltzmann machine; from logistic function to boltzmann distribution

machine-learning neural-networks deep-learning deep-belief-networks

asked Nov 22, 2016 at 15:22

2 votes

1 answer

603 views

correlation and independence: common mistake?

correlation independence linear pearson-r

asked Dec 17, 2017 at 18:47

1 vote

1 answer

163 views

logistic regression - why we forget assumption on data?

logistic classification normal-distribution covariance-matrix sigmoid-curve

asked Dec 23, 2017 at 9:55

1 vote

0 answers

22 views

reproducing kernel hilbert space notation

kernel-trick notation transfer-learning domain-adaptation

asked May 30 at 11:42

1 vote

1 answer

61 views

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

python gradient-descent backpropagation automatic-differentiation

asked Jun 5, 2020 at 9:34

1 vote

1 answer

88 views

simply demostration on conditioned probability

probability conditional-probability graphical-model bayesian-network

asked Aug 17, 2014 at 22:15

1 vote

0 answers

40 views

sampling: question about variance estimation

variance estimation sampling mean monte-carlo

asked Oct 9, 2017 at 9:38

0 votes

0 answers

1k views

Expectation Maximization (EM) stopping criterion

mathematical-statistics likelihood expectation-maximization optimal-stopping

asked Oct 2, 2019 at 14:42

Stack Exchange Network

current community

your communities

more stack exchange communities

19 Questions

gradient descent and local maximum

SciKit Learn: Multilayer perceptron early stopping, restore best weights

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

conjugate prior: is ever the best choice?

cross entropy loss max value

ICA: a question about the non-gaussian requirement

Expectation Maximization EM: is possibile in every case?

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

Definition of Bayesian network

Boltzmann machines: learning algorithm

Why do DeconvNet use ReLU in the backward pass?

boltzmann machine; from logistic function to boltzmann distribution

correlation and independence: common mistake?

logistic regression - why we forget assumption on data?

reproducing kernel hilbert space notation

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

simply demostration on conditioned probability

sampling: question about variance estimation

Expectation Maximization (EM) stopping criterion