Network profile

volperossa

Reputation

545

2018
2019
2020
2021

Top tag

neural-networks

Next privilege

1,000 Rep.

See votes

Badges

Newest

Notable Question

Next badge

0/1

Impact

0 posts edited

0 helpful flags

96 votes cast

19 Questions

Votes Activity Newest Views

votes

answer

views

gradient descent and local maximum

Aug 14 '18 at 5:08 Skander H. 9,942

votes

answers

289

views

SciKit Learn: Multilayer perceptron early stopping, restore best weights

neural-networks scikit-learn perceptron

Apr 14 '20 at 11:00 PAF 415

votes

answer

views

cross entropy loss max value

loss-functions extreme-value cross-entropy

Feb 15 '19 at 14:47 gunes 42.9k

votes

answers

731

views

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

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

Sep 27 '18 at 17:40 eric_kernfeld 4,557

votes

answers

795

views

conjugate prior: is ever the best choice?

bayesian maximum-likelihood prior hyperparameter conjugate-prior

Apr 16 '17 at 17:36 kjetil b halvorsen♦ 54.7k

votes

answers

views

ICA: a question about the non-gaussian requirement

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

Dec 18 at 19:54 volperossa 545

votes

answer

views

Expectation Maximization EM: is possibile in every case?

maximum-likelihood random-variable likelihood expectation-maximization

Apr 19 '17 at 21:03 jkpate 958

votes

answer

171

views

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

differential-privacy

Mar 24 at 16:04 Community♦ 1

votes

answer

171

views

Why do DeconvNet use ReLU in the backward pass?

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

Mar 30 '20 at 17:56 volperossa 545

votes

answer

237

views

Definition of Bayesian network

probability bayesian conditional-probability graphical-model bayesian-network

Jul 27 '17 at 8:33 Tim♦ 90.3k

votes

answers

162

views

boltzmann machine; from logistic function to boltzmann distribution

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

May 12 '17 at 22:23 amoeba 87.4k

votes

answer

181

views

Boltzmann machines: learning algorithm

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

Apr 23 '17 at 18:44 convolutionBoy 111

vote

answers

128

views

logistic regression - why we forget assumption on data?

logistic classification normal-distribution covariance-matrix sigmoid-curve

Dec 23 '17 at 13:06 volperossa 545

vote

answers

views

sampling: question about variance estimation

variance estimation sampling mean monte-carlo

Oct 9 '17 at 9:38 volperossa 545

votes

answers

views

why is the signal divided into epochs in EEG classification?

classification signal-processing moving-window

Dec 7 at 15:20 volperossa 545

votes

answer

views

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

python gradient-descent backpropagation automatic-differentiation

Jun 6 at 4:59 shimao 19.1k

votes

answers

465

views

Expectation Maximization (EM) stopping criterion

mathematical-statistics likelihood expectation-maximization optimal-stopping

Oct 2 '19 at 14:42 volperossa 545

votes

answer

394

views

correlation and independence: common mistake?

correlation independence linear pearson-r

Sep 13 '18 at 11:11 Peter Flom 91.7k

votes

answer

views

simply demostration on conditioned probability

probability conditional-probability graphical-model bayesian-network

Aug 18 '14 at 10:33 volperossa 545

Stack Exchange Network

current community

your communities

more stack exchange communities

Next privilege

Next badge

19 Questions

gradient descent and local maximum

SciKit Learn: Multilayer perceptron early stopping, restore best weights

cross entropy loss max value

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

conjugate prior: is ever the best choice?

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?

Why do DeconvNet use ReLU in the backward pass?

Definition of Bayesian network

boltzmann machine; from logistic function to boltzmann distribution

Boltzmann machines: learning algorithm

logistic regression - why we forget assumption on data?

sampling: question about variance estimation

why is the signal divided into epochs in EEG classification?

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

Expectation Maximization (EM) stopping criterion

correlation and independence: common mistake?

simply demostration on conditioned probability