Evolution of Activation Functions: An Empirical Investigation
| Autor: | Danielle Azar, Andrew Nader |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Artificial neural network Computer science business.industry Deep learning Evolutionary algorithm Computer Science - Neural and Evolutionary Computing Genetic programming 02 engineering and technology Trial and error Machine learning computer.software_genre Evolutionary computation 03 medical and health sciences 0302 clinical medicine Search algorithm Robustness (computer science) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Neural and Evolutionary Computing (cs.NE) Artificial intelligence business computer 030217 neurology & neurosurgery |
| Zdroj: | ACM Transactions on Evolutionary Learning and Optimization. 1:1-36 |
| ISSN: | 2688-3007 2688-299X |
| Popis: | The hyper-parameters of a neural network are traditionally designed through a time-consuming process of trial and error that requires substantial expert knowledge. Neural Architecture Search algorithms aim to take the human out of the loop by automatically finding a good set of hyper-parameters for the problem at hand. These algorithms have mostly focused on hyper-parameters such as the architectural configurations of the hidden layers and the connectivity of the hidden neurons, but there has been relatively little work on automating the search for completely new activation functions, which are one of the most crucial hyperparameters to choose. There are some widely used activation functions nowadays that are simple and work well, but nonetheless, there has been some interest in finding better activation functions. The work in the literature has mostly focused on designing new activation functions by hand or choosing from a set of predefined functions while this work presents an evolutionary algorithm to automate the search for completely new activation functions. We compare these new evolved activation functions to other existing and commonly used activation functions. The results are favorable and are obtained from averaging the performance of the activation functions found over 30 runs, with experiments being conducted on 10 different datasets and architectures to ensure the statistical robustness of the study. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|