User Recessive

4 votes

What is the relationship between the size of the hidden layer and the size of the cell state layer in an LSTM?

answered Sep 30, 2019 at 4:24

3 votes

What's the function that SGD takes to calculate the gradient?

answered Jan 14, 2020 at 23:34

3 votes

Accepted

What are possible ways to combat overfitting or improve the test accuracy in my case?

answered Mar 24, 2021 at 23:52

3 votes

Accepted

Bias equal to 1 and neuron output equal to -1 in neural networks

answered Nov 18, 2021 at 4:04

2 votes

Accepted

How do we know that the neurons of an artificial neural network start by learning small features?

answered Feb 26, 2021 at 4:46

2 votes

Accepted

How can I address missing values for LSTM?

answered Jul 13, 2021 at 1:18

2 votes

Do we need non-linear activation function in neural networks whose task isn't classification?

answered Sep 24, 2020 at 4:08

2 votes

Accepted

In a neural network, can colors be used for neurons in place of floating points and would there be any benefit in doing so?

answered Feb 14, 2020 at 5:01

2 votes

Accepted

Can GANs be used to generate something other than images?

answered Jul 23, 2020 at 0:20

2 votes

Why does a neuron in a multi-layer network need several input connections?

answered Jul 30, 2020 at 2:23

2 votes

Accepted

What are the reasons behind slow YOLO training?

answered Feb 28, 2020 at 5:21

2 votes

Can you provide some pseudocode examples of what constitutes an AI?

answered Mar 5, 2020 at 2:55

2 votes

Accepted

How do LSTM or GRU gates learn to specialize in their desired tasks?

answered Jun 5, 2020 at 4:21

2 votes

How to express accuracy of a regression ANN that uses MSE loss function?

answered Sep 14, 2019 at 0:50

2 votes

Accepted

How do layers in an artificial neural network transform inputs to outputs?

answered Jul 22, 2019 at 3:57

2 votes

How can I detect moving objects in a video by OpenCV without using deep learning techniques?

answered Dec 2, 2019 at 5:06

2 votes

Accepted

When using Neural Architecture Search, how are the hyper-parameters chosen?

answered Oct 30, 2019 at 5:33

2 votes

Accepted

What makes GAN or VAE better at image generation than NN that directly maps inputs to images

answered Dec 12, 2019 at 5:46

2 votes

Accepted

Do all neurons in a layer have the same activation function?

answered Dec 30, 2019 at 0:27

1 vote

Is artificial intelligence really just human intelligence?

answered Nov 20, 2019 at 2:05

1 vote

How can I find what does an specific neuron do in neural network?

answered Dec 6, 2019 at 3:09

1 vote

To deal with infinite loops, should I do a deeper search of the best moves with the same value, in alpha-beta pruning?

answered Dec 6, 2019 at 3:29

1 vote

Accepted

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

answered Jul 23, 2019 at 5:12

1 vote

Accepted

Understanding arrangement of applying filters to input channels

answered Jul 26, 2019 at 2:50

1 vote

Is the gradient at a layer independent of the activations of the previous layers?

answered Oct 11, 2019 at 5:33

1 vote

How should I design this LSTM network to perform stock prediction?

answered Jan 30, 2020 at 2:09

1 vote

Accepted

What is the neuron-level math behind backpropagation for a neural network?

answered Jan 9, 2020 at 1:01

1 vote

Accepted

Should I remove the text overlaying some images in the dataset before training the CNN?

answered Sep 18, 2020 at 4:54

1 vote

Can a NN be configured to indicate which points of the input influenced its prediction and how?

answered Feb 20, 2020 at 2:06

1 vote

Accepted

Flatten image using Neural network and matrix transpose

answered Sep 25, 2020 at 6:37

Stack Exchange Network

46 Answers

What is the relationship between the size of the hidden layer and the size of the cell state layer in an LSTM?

What's the function that SGD takes to calculate the gradient?

What are possible ways to combat overfitting or improve the test accuracy in my case?

Bias equal to 1 and neuron output equal to -1 in neural networks

How do we know that the neurons of an artificial neural network start by learning small features?

How can I address missing values for LSTM?

Do we need non-linear activation function in neural networks whose task isn't classification?

In a neural network, can colors be used for neurons in place of floating points and would there be any benefit in doing so?

Can GANs be used to generate something other than images?

Why does a neuron in a multi-layer network need several input connections?

What are the reasons behind slow YOLO training?

Can you provide some pseudocode examples of what constitutes an AI?

How do LSTM or GRU gates learn to specialize in their desired tasks?

How to express accuracy of a regression ANN that uses MSE loss function?

How do layers in an artificial neural network transform inputs to outputs?

How can I detect moving objects in a video by OpenCV without using deep learning techniques?

When using Neural Architecture Search, how are the hyper-parameters chosen?

What makes GAN or VAE better at image generation than NN that directly maps inputs to images

Do all neurons in a layer have the same activation function?

Is artificial intelligence really just human intelligence?

How can I find what does an specific neuron do in neural network?

To deal with infinite loops, should I do a deeper search of the best moves with the same value, in alpha-beta pruning?

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

Understanding arrangement of applying filters to input channels

Is the gradient at a layer independent of the activations of the previous layers?

How should I design this LSTM network to perform stock prediction?

What is the neuron-level math behind backpropagation for a neural network?

Should I remove the text overlaying some images in the dataset before training the CNN?

Can a NN be configured to indicate which points of the input influenced its prediction and how?

Flatten image using Neural network and matrix transpose