Questions tagged [hyper-parameters]

For questions related to the hyper-parameters of AI models and algorithms, which are parameters that are set before the learning process begins. For example, the number of hidden layers in a feed-forward neural network is usually a hyper-parameter.

Filter by
Sorted by
Tagged with
3
votes
0answers
27 views

How can I do hyperparameter optimization for a CNN-LSTM neural network?

I have built a CNN-LSTM neural network with 2 inputs and 2 outputs in Keras. I trained the network with model.fit_generator() (and not ...
2
votes
0answers
13 views

Which CNN hyper-parameters are most sensitive to centered versus off centered data?

Which hyper-parameters of a convolutional neural network are likely to be the most sensitive to depending on whether the training (and test and inference) data involves only accurately centered images ...
3
votes
0answers
17 views

How to organize model training hyperparameters

I am working on multiple deep learning projects, most of them in the area of computer vision. For many of them I create multiple models, try different approaches, use various model architectures. And ...
2
votes
1answer
24 views

Will a .h5 file trained with Xception model work with Resnet50?

I have been running my 2013 server box since 2 weeks ago for training an AI model. I set up 30 epochs to run but since than it only ran 1 epoch as my PC config is super slow. But it generates 1 .h5 ...
1
vote
2answers
42 views

Does this hyperparameter optimisation approach yield the optimal hyperparameters?

Say I have a ML model which is not very costly to train. It has around say 5 hyperparameters. One way to select best hyperparameters would be to keep all the other hyperparamaters fixed and train ...
2
votes
1answer
67 views

Can we automate the choice of the hyper-parameters of the evolutionary algorithms?

Certain hyper-parameters (e.g. the size of the offspring generation or the definition of the fitness function) and the design (e.g. how the mutation is performed) of evolutionary algorithms usually ...
2
votes
0answers
24 views

What is the benefit of scaling the hyperparameter C of an SVM?

Please read the following page of the Sklearn documentation. The figure shown there (see below) illustrates why C should be scaled when using a SVM with 'l1' penalty, whereas it shouldn't be scaled ...
8
votes
1answer
121 views

What causes a model to require a low learning rate?

I've pondered this for a while without developing an intuition for the math behind the cause of this. So what causes a model to need a low learning rate?
0
votes
0answers
24 views

Feature selection optimization and hyperparameters optimization for one model

Question is purely theoretical. I am desiging a machine learning model for classification purposes. I am using GridSearch optimization method to select best hyperparameters and I have written ...
3
votes
1answer
47 views

How do you efficiently choose the hyper-parameters of a neural network?

How do you efficiently choose the hyper-parameters of a neural network (e.g. the learning rate, number of layer, weights, etc.)?
6
votes
1answer
295 views

How should we choose the dimensions of the encoding layer in auto-encoders?

How should we choose the dimensions of the encoding layer in auto-encoders?
2
votes
1answer
113 views

Maximum number of neurons in a layer given number of neurons in previous layer

Consider an extremely complicated feed-forward neural network training example but with no need of computational efficiency or limiting of processing time. What is the maximum number of hidden ...
0
votes
1answer
45 views

How many trees should be generated in a random forest?

What are ways of determining the number of trees to be generated in a random forest algorithm?
2
votes
1answer
86 views

Is a calculus or ML approach to varying learning rate as a function of loss and epoch been investigated?

Many have examined the idea of modifying learning rate at discrete times during the training of an artificial network using conventional back propagation. The goals of such work have been a balance ...
7
votes
3answers
5k views

How do we choose the kernel size depending on the problem?

Obviously, finding suitable hyper-parameters for a neural network is a complex task and very problem or domain-specific. However, there should be at least some "rules" that hold most times for filter ...