DENSER: deep evolutionary network structured representation. Deep Evolutionary Network Structured Representation (DENSER) is a novel approach to automatically design Artificial Neural Networks (ANNs) using Evolutionary Computation. The algorithm not only searches for the best network topology, but also tunes hyper-parameters (e.g., learning or data augmentation parameters). The automatic design is achieved using a representation with two distinct levels, where the outer level encodes the general structure of the network, and the inner level encodes the parameters associated with each layer. The allowed layers and hyper-parameter value ranges are defined by means of a human-readable Context-Free Grammar.
Keywords for this software
References in zbMATH (referenced in 3 articles )
Showing results 1 to 3 of 3.
- Filipe Assunção, Nuno Lourenço, Bernardete Ribeiro, Penousal Machado: Fast-DENSER: Fast Deep Evolutionary Network Structured Representation (2021) not zbMATH
- George Kyriakides, Konstantinos Margaritis: NORD: A python framework for Neural Architecture Search (2020) not zbMATH
- Gu, Xue; Meng, Ziyao; Liang, Yanchun; Xu, Dong; Huang, Han; Han, Xiaosong; et al.: ESAE: evolutionary strategy-based architecture evolution (2020)