Hot answers tagged

4 votes
Accepted

Is it possible to train a neural network with 3 inputs and 12 outputs?

There is nothing stopping you, you can setup Dense Neural Networks to have any size inputs or outputs (simple proof is to imagine a single layer NN with no activation is just a linear transform and ...
  • 2,319
3 votes

Is it possible to classify data using a genetic algorithm?

It is possible, but is a pretty terrible idea. There are a few options. One is to not use the GA as a direct classifier, but instead use a GA to learn the parameters of another classification model ...
  • 581
3 votes
Accepted

How can I train a neural network if I don't have enough data?

You can synthetically increase the number of samples. For example with augmentation or unsupervised adaption (Self-training). With augmentation you grant the system way more robustness so i would ...
2 votes

How can I use a trained CNN to predict a new image label?

As the question has been left unanswered, for future readers of the questions: The documentation you link gives the answer to your question. Given the fact you have a pre-trained model as you say: <...
  • 260
2 votes

Is it possible to classify data using a genetic algorithm?

You must understand that a genetic algorithm is an optimization algorithm. You can't feed it e-mails and make it classify spam. A genetic algorithm is used to train a model to classify spam. That ...
2 votes

How to use computer vision to find corners of a soccer field based on location coordinates?

Finding lines in an image often leads to the Hough line transform. Many libraries implement it, including OpenCV. Getting the lines should answer subsequent questions (and it doesn't, please consider ...
  • 1,490
2 votes
Accepted

On what basis is MATLAB "inflexible" to perform ML/AI research on it?

(This question is could be considered off-topic or opinion-based, but I will answer it by providing facts that could hinder the adoption of MATLAB by AI researchers). There are 2 main reasons why ...
  • 35.5k
1 vote
Accepted

Question regarding matlab computer vision application and color recongnition

2 Yes, cracks and in general defects detection is a task performed with neural networks and deep learning, but depending on your specific use case it might be an overkill. You talk about pixel to ...
1 vote

Semantic segmentation CNN outputs all zeroes

Similar to other answers, I don't know Matlab that well but you could try the following steps to debug your problem. Make sure you can overfit to a single instance from your dataset, pull out a single ...
1 vote

How can I train a neural network if I don't have enough data?

In theory, yes, using synthetic data generation. This involves applying transformations to the original images to generate new 'unique' images. Some standard techniques include rotating, flipping, ...
  • 156
1 vote

Is it possible to train a neural network with 3 inputs and 12 outputs?

The perceptron convergence theorem states that any architecture will lead to a correlation between the data. Yes, you can!
1 vote
Accepted

How can I test my trained network on the next unavailable hour?

You need to have access to the 696th hour (or successive hours), otherwise, you cannot test your model. An alternative would be, for example, to train your model on the first 693 hours, validate it on ...
  • 35.5k
1 vote

Is it possible to use a trained neural network to predict a feature, given other features and output?

From your question, it appears that you would like to use other features in your data to predict one of the features. I am not sure I understood your question clearly, but anyways, either, you would ...
  • 225
1 vote
Accepted

How to use computer vision to find corners of a soccer field based on location coordinates?

I assume that you are familiar with homogeneous transformations and the meaning of global and local coordinate frames. If not, global frame is the fixed frame; a reference frame for your whole problem,...
  • 241
1 vote

Is it a valid Deep Neural Network?

Yes, it is a very common practice to use some RNN when your input data is a sequence. Besides, your network has some shape issue if your input data is 2D. You should, at least flatten your input data ...
1 vote
Accepted

Reinforcement learning for robotic motion planning - Problem statement ideas

I think that this may be too difficult for only a few weeks of work. There are a few reasons why and although all of the reasons are themselves learning opportunities, it may cost you more time than ...

Only top scored, non community-wiki answers of a minimum length are eligible