Joint Lectures on Evolutionary Algorithms (JoLEA)
- Wednesday 2 November 2022
Neuroevolution, Trajectories and Landscapes
Neuroevolution, the use of evolutionary algorithms to design neural networks, has a long tradition in evolutionary computation with roots in the early 1990s. Traditionally, neuroevolution systems optimise both the neural network topology and its weights. However, when scaling up to contemporary deep models with millions of weights, gradient-based weight optimisation generally outperforms evolutionary methods. In consequence, many recent methods evolve the topology only. This approach is also known as Neural Architecture Search (NAS). This talk overviews our recent work on modelling neuroevolution and NAS systems with search trajectory networks (STNs) and local optima networks (LONs) with the aim of providing a visual and quantitative understanding of search and optimisation in this domain.
Gabriela Ochoa is a Professor of Computing Science at the University of Stirling in Scotland, UK. Her research lies in the foundations and applications of evolutionary algorithms and metaheuristics, with emphasis on adaptive search, fitness landscape analysis and visualisation. She holds a PhD from the University of Sussex, UK, and has held academic and research positions at the University Simon Bolivar, Venezuela, and the University of Nottingham, UK. Her recent work on network-based models of computational search enhances their descriptive and visualisation power, producing several publications including 4 best-paper awards and 8 other nominations at leading venues. She collaborates cross-disciplines to apply evolutionary computation in healthcare and conservation. She has been active in organisation and editorial roles within leading Evolutionary Computation outlets including the Genetic and Evolutionary Computation Conference (GECCO), the Evolutionary Computation Journal (ECJ) and the ACM Transactions on Evolutionary Learning and Optimisation (TELO). In 2020, she was recognised by the leading European event on bio-inspired algorithms, EvoStar, for her outstanding contributions to the field.
The series is organized by a team from four universities, initiated by prof. dr. Thomas Bäck (Leiden University), prof. dr. Peter A.N. Bosman (CWI), prof. dr. Gusz Eiben (Vrije Universiteit Amsterdam), and dr. ir. Dirk Thierens (Utrecht University).