- author = "Fergal Stapleton",
- title = "Semantic-Based Surrogate-Assisted Neuroevolution for Neural Architecture Search in Deep Neural Networks",
- school = "Hamilton Institute, National University of Ireland Maynooth",
- year = "2025",
- address = "Maynooth, Co. Kildare, Ireland",
- month = apr # " 11",
- keywords = "genetic algorithms, genetic programming, Neuro-Linear Genetic Programming, NeuroLGP, SAEA, NeuroLGP-MB Semantic-Based, Surrogate-Assisted, Neuroevolution, Neural Architecture, Deep Neural Networks, AI, ANN",
-
URL = "
https://mural.maynoothuniversity.ie/id/eprint/19997/",
-
URL = "
https://mural.maynoothuniversity.ie/id/eprint/19997/1/Thesis%20%281%29.pdf",
- size = "189 pages",
-
abstract = "Neuroevolution is a popular branch of Neural
Architecture Search (NAS) that searches for
high-performing artificial neural network architectures
using evolutionary algorithms. Neuroevolution of
deeper, more complex architectures, like deep neural
networks, however, comes at a great computational cost,
as often thousands of architectures need to be trained
and evaluated over numerous Graphical Processing Unit
days. To address this, research has turned to the use
of Surrogate-Assisted Evolutionary Algorithms (SAEAs),
where less expensive surrogate models can be used to
estimate the fitness of an architecture, without the
need to fully train it, resulting in a substantial
reduction in the associated computational cost.
Ultimately, SAEAs have emerged as a graceful response
to tackling computational intensive workflows, such as
neuroevolution, however, some notable limitations
remain, such as, issues relating to high-dimensionality
and complex encoding strategies required in current
surrogate-assisted neuroevolution methods.
we use a semantic-inspired method to adeptly handle these issues, which in turn, is incorporated into a novel technique named Neuro-Linear Genetic Programming (NeuroLGP). NeuroLGP evolves chain-structured topologies with a representation closely aligned to how neural network architectures are naturally constructed. This allows us to perform an in-depth analysis not only on the surrogate model robustness and architecture performance, but also allows us to analyse how the internal makeup of our architectures change during evolution. From this, we propose a new mechanism, named NeuroLGPMB, that is capable of evolving truly complex modern networks that exhibit multi-branch connections. Our proposed SAEA approach was shown to not only be robust for both NeuroLGP and NeuroLGP-MB but was also able to find high-performing individuals with a substantial reduction in time.",
-
notes = "also known as \cite{mu19997}
ICHEC, MeluXina, LuxProvide
Supervisor: Edgar Galvan-Lopez",
