User respectful

12 votes

Can digital computers understand infinity?

answered Oct 6, 2019 at 1:10

9 votes

Accepted

What is the benefit of using identity mapping layers in deep neural networks like ResNet?

answered Oct 6, 2019 at 4:10

8 votes

Accepted

How would an AI learn idiomatic phrases in a natural language?

answered Sep 5, 2019 at 15:51

4 votes

Accepted

Why not use the MSE instead of the current logistic regression?

answered Sep 5, 2019 at 0:34

4 votes

Accepted

Can two admissable heuristics not dominate each other?

answered Oct 3, 2019 at 1:40

3 votes

Accepted

Is there any computer vision technology that can detect any type of object?

answered Sep 7, 2019 at 3:51

3 votes

What does an oscillating validation error curve represent?

answered Sep 1, 2019 at 17:44

3 votes

Accepted

How does the forget layer of an LSTM work?

answered Dec 25, 2019 at 19:28

3 votes

Can we get the inverse of the function that a neural network represents?

answered Jan 18, 2020 at 23:41

2 votes

Accepted

Can multiple activation functions be replaced with a single activation function?

answered Oct 9, 2019 at 18:34

2 votes

Accepted

Can Neural Networks be considered as "Strong AI"?

answered Sep 1, 2019 at 4:33

1 vote

Recommend item from set based on features

answered Sep 1, 2019 at 5:47

1 vote

Which predictive algorithm is most appropriate for a proceeding situation?

answered Sep 1, 2019 at 17:05

1 vote

How should I design the LSTM architecture for multivariate time series forecasting problems?

answered Sep 2, 2019 at 16:30

1 vote

Issue at training simple RNN for word generation

answered Sep 6, 2019 at 21:37

1 vote

How do we choose the activation function for each hidden node?

answered Oct 12, 2019 at 17:50

1 vote

Accepted

What kind of data structures are needed to efficiently do back-propagation in a feedforward neural network?

answered Nov 10, 2019 at 4:51

1 vote

Can a trained object detection model deal with variations of the input?

answered Dec 7, 2019 at 23:20

1 vote

How to report the solution path of a search algorithm on a graph?

answered Feb 9, 2020 at 20:04

1 vote

Why is my derivation of the back-propagation equations inconsistent with Andrew Ng's slides from Coursera?

answered Mar 19, 2020 at 1:56

0 votes

How can I cluster based on the complementary categories?

answered Sep 1, 2019 at 5:36

Stack Exchange Network

21 Answers

Can digital computers understand infinity?

What is the benefit of using identity mapping layers in deep neural networks like ResNet?

How would an AI learn idiomatic phrases in a natural language?

Why not use the MSE instead of the current logistic regression?

Can two admissable heuristics not dominate each other?

Is there any computer vision technology that can detect any type of object?

What does an oscillating validation error curve represent?

How does the forget layer of an LSTM work?

Can we get the inverse of the function that a neural network represents?

Can multiple activation functions be replaced with a single activation function?

Can Neural Networks be considered as "Strong AI"?

Recommend item from set based on features

Which predictive algorithm is most appropriate for a proceeding situation?

How should I design the LSTM architecture for multivariate time series forecasting problems?

Issue at training simple RNN for word generation

How do we choose the activation function for each hidden node?

What kind of data structures are needed to efficiently do back-propagation in a feedforward neural network?

Can a trained object detection model deal with variations of the input?

How to report the solution path of a search algorithm on a graph?

Why is my derivation of the back-propagation equations inconsistent with Andrew Ng's slides from Coursera?

How can I cluster based on the complementary categories?