User Maxim

73 votes

Accepted

Do scientists know what is happening inside artificial neural networks?

answered Sep 17, 2017 at 10:03

23 votes

Accepted

How do I handle large images when training a CNN?

answered Oct 4, 2017 at 22:52

17 votes

How is it possible that deep neural networks are so easily fooled?

answered Sep 18, 2017 at 14:30

16 votes

Accepted

Why has the cross-entropy become the classification standard loss function and not Kullback-Leibler divergence?

answered Oct 4, 2017 at 13:04

14 votes

Accepted

Is it possible to train a neural network as new classes are given?

answered Sep 18, 2017 at 16:37

6 votes

What is the difference between a convolutional neural network and a regular neural network?

answered Mar 6, 2018 at 23:01

2 votes

Is overfitting always a bad thing?

answered Sep 30, 2017 at 17:32

2 votes

Accepted

How is creativity generated in a currently rule based neural network?

answered Oct 11, 2017 at 11:38

2 votes

Is there any free dataset of source code along with natural language description?

answered Oct 5, 2017 at 8:44

2 votes

How generate variation in datasets

answered Oct 6, 2017 at 6:46

2 votes

How to detect the empty parking spots?

answered Oct 7, 2017 at 23:21

1 vote

How do I know if my backpropagation is implemented correctly?

answered Oct 7, 2017 at 23:40

1 vote

Why do we need weights when training a perceptron as an OR gate?

answered Oct 20, 2017 at 21:00

1 vote

Accepted

What is $I$ in the noise described in the paper "Parameter Space Noise for Exploration"?

answered Oct 20, 2017 at 21:26

1 vote

What are the counterparts of non-linearities and dropout in fully convolutional networks?

answered Oct 11, 2017 at 4:58

1 vote

In a neural network given partial inputs and complete outputs, is it possible to predict remainig inputs

answered Sep 30, 2017 at 18:16

1 vote

Accepted

A good way to understand the mathematical details of variational autoencoders through implementation?

answered Sep 30, 2017 at 19:48

1 vote

Why is the change in cost wrt bias in neural network equal to error in the neuron?

answered Oct 1, 2017 at 16:05

1 vote

Understanding a paragraph about object detection with two objects

answered Oct 2, 2017 at 22:30

0 votes

Accepted

ReLu, Sum and Convolution Layers to Count Pixels of Certain Color

answered Oct 8, 2017 at 8:12

Stack Exchange Network

20 Answers

Do scientists know what is happening inside artificial neural networks?

How do I handle large images when training a CNN?

How is it possible that deep neural networks are so easily fooled?

Why has the cross-entropy become the classification standard loss function and not Kullback-Leibler divergence?

Is it possible to train a neural network as new classes are given?

What is the difference between a convolutional neural network and a regular neural network?

Is overfitting always a bad thing?

How is creativity generated in a currently rule based neural network?

Is there any free dataset of source code along with natural language description?

How generate variation in datasets

How to detect the empty parking spots?

How do I know if my backpropagation is implemented correctly?

Why do we need weights when training a perceptron as an OR gate?

What is $I$ in the noise described in the paper "Parameter Space Noise for Exploration"?

What are the counterparts of non-linearities and dropout in fully convolutional networks?

In a neural network given partial inputs and complete outputs, is it possible to predict remainig inputs

A good way to understand the mathematical details of variational autoencoders through implementation?

Why is the change in cost wrt bias in neural network equal to error in the neuron?

Understanding a paragraph about object detection with two objects

ReLu, Sum and Convolution Layers to Count Pixels of Certain Color