Automatic model selection for fully connected neural networks
| Autor: | Ghazaale Leylaz, Jian-Qiao Sun, Shangjie Frank Ma, Oliver Schütze, David Laredo |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Control and Optimization Computer science Crossover Evolutionary algorithm 02 engineering and technology Machine learning computer.software_genre 01 natural sciences 020901 industrial engineering & automation Encoding (memory) 0103 physical sciences Electrical and Electronic Engineering 010301 acoustics Civil and Structural Engineering Network architecture Fitness function Artificial neural network business.industry Mechanical Engineering Deep learning Model selection Control and Systems Engineering Modeling and Simulation Artificial intelligence business computer |
| Zdroj: | International Journal of Dynamics and Control. 8:1063-1079 |
| ISSN: | 2195-2698 2195-268X |
| DOI: | 10.1007/s40435-020-00708-w |
| Popis: | Neural networks and deep learning are changing the way that artificial intelligence is being done. Efficiently choosing a suitable network architecture and fine tuning its hyper-parameters for a specific dataset is a time-consuming task given the staggering number of possible alternatives. In this paper, we address the problem of model selection by means of a fully automated framework for efficiently selecting a neural network model for a selected task, whether it is classification or regression. The algorithm, named Automatic Model Selection, is a modified micro-genetic algorithm that automatically and efficiently finds the most suitable fully connected neural network model for a given dataset. The main contributions of this method are: a simple, list based encoding for neural networks, which will be used as the genotype in our evolutionary algorithm, novel crossover and mutation operators, the introduction of a fitness function that considers the accuracy of the neural network and its complexity, and a method to measure the similarity between two neural networks. AMS is evaluated on two different datasets. By comparing some models obtained with AMS to state-of-the-art models for each dataset we show that AMS can automatically find efficient neural network models. Furthermore, AMS is computationally efficient and can make use of distributed computing paradigms to further boost its performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink