User NikoNyrh

3 votes

Accepted

Are these book example CNN results realistic?

answered Jan 5, 2022 at 20:13

3 votes

Why is a simple regression problem so hard for an MLP to learn?

answered Jan 9 at 18:12

2 votes

How to detect outlier images?

answered Mar 13 at 12:53

2 votes

Are there any algorithms (even backtracking variations) that solve the sudoku in a way more similar to this approach?

answered Jan 6, 2022 at 11:41

2 votes

How are OCR training datasets constructed?

answered Oct 27, 2022 at 13:15

1 vote

How to deactivate kernels from a trained CNN model

answered Oct 19, 2022 at 11:59

1 vote

SQL Machine Learning using matrix multiplication

answered Oct 25, 2022 at 13:58

1 vote

Accepted

Why do we need Tensorflow, Keras and other ML/AI modules?

answered Sep 27, 2022 at 11:42

1 vote

Is Computer Vision always related to Machine Learning?

answered Sep 29, 2022 at 12:37

1 vote

Can I find a mapping that minimizes the maximum distance ratio of certain vectors?

answered May 20, 2020 at 14:06

1 vote

Usability of power series in AI analysis

answered May 11, 2022 at 12:37

1 vote

I have a 3 class classification problem. Detection of one of classes is very important. How to design the problem? one class classification or ...?

answered May 20, 2022 at 12:57

1 vote

How to calculate the total number of inputs in CNN?

answered Jul 1, 2022 at 9:39

1 vote

Is my intuition about RNN wrong?

answered Jan 6, 2022 at 14:01

1 vote

Can CNNs detect image similarity?

answered Jan 5, 2022 at 20:43

1 vote

Is there a way to use AI to compare thousands of files and detect the ones containing "unusual" content?

answered Jan 5, 2022 at 21:06

1 vote

How to make NN distinguish between two types of functions (data)?

answered Jan 5, 2022 at 22:07

1 vote

My accuracy wont improve in tensorflow

answered Jan 9, 2022 at 15:52

1 vote

Should batch-normalization/dropout/activation-function layers be used after the last fully connected layer?

answered Jan 18, 2022 at 15:33

1 vote

Why does validation accuracy stop rising so soon?

answered Jan 19, 2022 at 18:31

1 vote

How to classify two very similar images using Deep Learning?

answered Jan 19, 2022 at 18:54

1 vote

Accepted

Are any non-injective activation functions used?

answered Jan 24, 2022 at 22:41

1 vote

How can the input order of pairs into a neural network not matter (i.e. symmetry)?

answered Jan 27, 2022 at 20:07

1 vote

Accepted

How to construct input dependent convolutional filter?

answered Feb 8, 2022 at 17:44

1 vote

Image segmentation when given masking information is incomplete

answered Feb 8, 2022 at 20:03

1 vote

how to detect ouliers in audio dataset?

answered Feb 13, 2022 at 11:53

1 vote

Are there any scale invariant activation functions that outputs probability distribution?

answered Feb 16, 2022 at 9:42

1 vote

Formally, what are the layers in an Artificial Neural Network?

answered Feb 10 at 17:09

1 vote

Would it be a problem to use non-squared images for a CNN model?

answered Jan 27 at 16:17

1 vote

Accepted

Does a constant background in training data affect image classification model's performance?

answered Nov 3, 2022 at 16:58

Stack Exchange Network

47 Answers

Are these book example CNN results realistic?

Why is a simple regression problem so hard for an MLP to learn?

How to detect outlier images?

Are there any algorithms (even backtracking variations) that solve the sudoku in a way more similar to this approach?

How are OCR training datasets constructed?

How to deactivate kernels from a trained CNN model

SQL Machine Learning using matrix multiplication

Why do we need Tensorflow, Keras and other ML/AI modules?

Is Computer Vision always related to Machine Learning?

Can I find a mapping that minimizes the maximum distance ratio of certain vectors?

Usability of power series in AI analysis

I have a 3 class classification problem. Detection of one of classes is very important. How to design the problem? one class classification or ...?

How to calculate the total number of inputs in CNN?

Is my intuition about RNN wrong?

Can CNNs detect image similarity?

Is there a way to use AI to compare thousands of files and detect the ones containing "unusual" content?

How to make NN distinguish between two types of functions (data)?

My accuracy wont improve in tensorflow

Should batch-normalization/dropout/activation-function layers be used after the last fully connected layer?

Why does validation accuracy stop rising so soon?

How to classify two very similar images using Deep Learning?

Are any non-injective activation functions used?

How can the input order of pairs into a neural network not matter (i.e. symmetry)?

How to construct input dependent convolutional filter?

Image segmentation when given masking information is incomplete

how to detect ouliers in audio dataset?

Are there any scale invariant activation functions that outputs probability distribution?

Formally, what are the layers in an Artificial Neural Network?

Would it be a problem to use non-squared images for a CNN model?

Does a constant background in training data affect image classification model's performance?