Network profile

Recessive

Reputation

1,126

1.1k
943
760

Next tag badge

neural-networks

29/100 score

19/20 answers

Badges

Newest

Next badge

0/1

Impact

2 posts edited

2 helpful flags

157 votes cast

16 Questions

Votes Activity Newest Views

votes

answers

views

Does using the softmax function in Q learning not defeat the purpose of Q learning?

reinforcement-learning q-learning

Jun 23 '20 at 8:02 YuCheng Yang 1

votes

answer

views

Why is the learning rate generally beneath 1?

Nov 29 at 12:25 nbro♦ 27.3k

votes

answers

views

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

neural-networks long-short-term-memory

Jan 18 '20 at 2:37 Recessive 1,126

votes

answer

views

In unsupervised learning, what is meant by “finding the probability of an image”?

unsupervised-learning

Dec 6 '19 at 17:35 Diego Gomez 373

votes

answer

views

Structure discrepancy of an LSTM?

neural-networks backpropagation long-short-term-memory

Sep 8 '19 at 5:05 mshlis 2,149

votes

answer

144

views

How are exploding numbers in a forward pass of a CNN combated?

machine-learning convolutional-neural-networks relu

Jun 28 '19 at 10:51 nbro♦ 27.3k

votes

answer

views

How is a neural network where the majority of inputs are 0 trained?

convolutional-neural-networks training backpropagation alexnet

Jun 12 '20 at 23:52 nbro♦ 27.3k

votes

answers

106

views

How is the bias caused by a max pooling layer overcome?

machine-learning convolutional-neural-networks relu bias-variance-tradeoff

Nov 20 '19 at 1:55 Pluviophile 1,081

votes

answer

views

Why does an LSTM cycle on initialisation?

long-short-term-memory

Oct 8 '19 at 0:38 nbro♦ 27.3k

vote

answer

139

views

Dropout causes too much noise for network to train

neural-networks convolutional-neural-networks dropout regularization relu

Apr 8 at 15:08 Community♦ 1

vote

answer

views

Is the following the correct implementation of the Q learning algorithm for a neural network?

neural-networks q-learning

Dec 9 '19 at 14:36 Neil Slater 18.9k

vote

answers

views

What are the standard problems for CNNs and LSTMs?

convolutional-neural-networks long-short-term-memory

Oct 20 '19 at 15:07 nbro♦ 27.3k

votes

answer

views

Positive bias causes the calculation of incorrect gradients

convolutional-neural-networks backpropagation

Mar 9 at 7:06 Community♦ 1

votes

answer

110

views

Possible model to use to find pixel locations of objects

convolutional-neural-networks object-detection regression

Mar 3 at 11:06 Community♦ 1

votes

answer

109

views

How does an LSTM output the correct dimensions for classes?

long-short-term-memory

Sep 3 '19 at 3:53 Recessive 1,126

votes

answer

views

Is it possible with stochastic gradient descent for the error to increase?

neural-networks gradient-descent loss-functions

Jul 10 '19 at 5:33 mirror2image 615

Stack Exchange Network

current community

your communities

more stack exchange communities

Next badge

16 Questions

Does using the softmax function in Q learning not defeat the purpose of Q learning?

Why is the learning rate generally beneath 1?

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

In unsupervised learning, what is meant by “finding the probability of an image”?

Structure discrepancy of an LSTM?

How are exploding numbers in a forward pass of a CNN combated?

How is a neural network where the majority of inputs are 0 trained?

How is the bias caused by a max pooling layer overcome?

Why does an LSTM cycle on initialisation?

Dropout causes too much noise for network to train

Is the following the correct implementation of the Q learning algorithm for a neural network?

What are the standard problems for CNNs and LSTMs?

Positive bias causes the calculation of incorrect gradients

Possible model to use to find pixel locations of objects

How does an LSTM output the correct dimensions for classes?

Is it possible with stochastic gradient descent for the error to increase?