Complexity-based speciation and genotype representation for neuroevolution

Hadjiivanov, Alexander; Blair, Alan

doi:10.1109/cec.2016.7744180

Cited by 4 publications

(2 citation statements)

References 22 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In previous research [29], we proposed a NE framework (named Cortex) which is based on a direct genotype encoding using the ordered number of nodes in an unstructured network as a straightforward metric for matching network topologies during crossover. In this study, Cortex is extended to make it applicable to deep layered NNs, with particular focus on deep CNNs.…”

Section: Bmentioning

confidence: 99%

Epigenetic evolution of deep convolutional models

Hadjiivanov

Blair

2019

2019 IEEE Congress on Evolutionary Computation (CEC)

Self Cite

View full text Add to dashboard Cite

In this study, we build upon a previously proposed neuroevolution framework to evolve deep convolutional models. Specifically, the genome encoding and the crossover operator are extended to make them applicable to layered networks. We also propose a convolutional layer layout which allows kernels of different shapes and sizes to coexist within the same layer, and present an argument as to why this may be beneficial. The proposed layout enables the size and shape of individual kernels within a convolutional layer to be evolved with a corresponding new mutation operator. The proposed framework employs a hybrid optimisation strategy involving structural changes through epigenetic evolution and weight update through backpropagation in a population-based setting. Experiments on several image classification benchmarks demonstrate that the crossover operator is sufficiently robust to produce increasingly performant offspring even when the parents are trained on only a small random subset of the training dataset in each epoch, thus providing direct confirmation that learned features and behaviour can be successfully transferred from parent networks to offspring in the next generation.

show abstract

Section: Bmentioning

confidence: 99%

Epigenetic evolution of deep convolutional models

Hadjiivanov

Blair

2019

2019 IEEE Congress on Evolutionary Computation (CEC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another speciation algorithm, Natural Evolution Speciation for NEAT (NENEAT) [12], replaces NEAT's speciation with a cladistic strategy where all the genomes in a species share a subset of nodes. Hadjiivanov et al designed a complexity-based speciation strategy, which grouped genomes by the number of hidden neurons [13]. Verbancsics et al investigated the effect of crossover and mutation on neuroevolution speciation strategies [14].…”

Section: Introductionmentioning

confidence: 99%

Improving Neuroevolution Using Island Extinction and Repopulation

Lyu,

Karns,

ElSaid

et al. 2020

Preprint

View full text Add to dashboard Cite

Neuroevolution commonly uses speciation strategies to better explore the search space of neural network architectures. One such speciation strategy is through the use of islands, which are also popular in improving performance and convergence of distributed evolutionary algorithms. However, in this approach some islands can become stagnant and not find new best solutions. In this paper, we propose utilizing extinction events and island repopulation to avoid premature convergence. We explore this with the Evolutionary eXploration of Augmenting Memory Models (EXAMM) neuro-evolution algorithm. In this strategy, all members of the worst performing island are killed of periodically and repopulated with mutated versions of the global best genome. This island based strategy is additionally compared to NEAT's (NeuroEvolution of Augmenting Topologies) speciation strategy. Experiments were performed using two different real world time series datasets (coal-fired power plant and aviation flight data). The results show that with statistical significance, this island extinction and repopulation strategy evolves better global best genomes than both EXAMM's original island based strategy and NEAT's speciation strategy.

show abstract