Weighted Random Search for CNN Hyperparameter Optimization

Nearly all model algorithms used in machine learning use two different sets of parameters: the training parameters and the meta-parameters (hyperparameters). While the training parameters are learned during the training phase, the values of the hyperparameters have to be specified before learning st...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of computers, communications & control Vol. 15; no. 2
Main Authors Andonie, Razvan, Florea, Adrian-Catalin
Format Journal Article
LanguageEnglish
Published Oradea Agora University of Oradea 01.04.2020
Subjects
Algorithms
Artificial neural networks
Computer applications
Learning algorithms
Machine learning
Neural networks
Optimization
Parameters
Searching
Training
Online AccessGet full text

Cover

More Information
Summary:Nearly all model algorithms used in machine learning use two different sets of parameters: the training parameters and the meta-parameters (hyperparameters). While the training parameters are learned during the training phase, the values of the hyperparameters have to be specified before learning starts. For a given dataset, we would like to find the optimal combination of hyperparameter values, in a reasonable amount of time. This is a challenging task because of its computational complexity. In previous work [11], we introduced the Weighted Random Search (WRS) method, a combination of Random Search (RS) and probabilistic greedy heuristic. In the current paper, we compare the WRS method with several state-of-the art hyperparameter optimization methods with respect to Convolutional Neural Network (CNN) hyperparameter optimization. The criterion is the classification accuracy achieved within the same number of tested combinations of hyperparameter values. According to our experiments, the WRS algorithm outperforms the other methods.
ISSN:1841-9836
1841-9844
DOI:10.15837/ijccc.2020.2.3868