@misc{10481/108947,
year = {2025},
month = {3},
url = {https://hdl.handle.net/10481/108947},
abstract = {The design of Artificial Neural Networks (ANN) is critical for their performance. The research field called
Neural Network Search (NAS) investigates automated design strategies. This work proposes a novel NAS stack
that stands out in three facets. First, the representation scheme encodes problem-specific ANN as plain vectors
of numbers without needing auxiliary conversion models. Second, it is a pioneer in relying on the TLBO meta-
heuristic. This optimizer supports large-scale problems and only expects two parameters, contrasting with other
meta-heuristics used for NAS. Third, the stack includes a new evaluation predictor that avoids evaluating non-
promising architectures. It combines several machine learning methods that train as the optimizer evaluates
solutions, which avoids preliminary preparing this component and makes it self-adaptive. The proposal has
been tested by using it to build a CIFAR-10 classifier while forcing the architecture to have fewer than
150,000 parameters, assuming that the resulting network must be deployed in a resource-constrained IoT
device. The designs found with and without the predictor achieve validation accuracies of 78.68% and 80.65%,
respectively. Both outperform a larger model from the recent literature. The predictor slightly constraints the
evolution of solutions, but it approximately halves the computational effort. After extending the test to the
CIFAR-100 dataset, the proposal achieves a validation accuracy of 65.43% with 478,006 parameters in its
fastest configuration, competing with current results in the literature.},
organization = {IMOCO4.E (EU H2020 RIA-101007311) (PCI2021-1219257) from MCIN/AEI/10.13039/501100011033 and EU NextGenerationEU/PRTR},
organization = {R+D+i PID2021-123278OB-I00 and PDC2022-133370-I00 from MCI-N/AEI/10.13039/501100 011033},
organization = {(FPU19/02756)},
organization = {(PAIDI 2021: POSTDOC_21_00124)},
publisher = {Elsevier},
keywords = {Artificial neural networks},
keywords = {Neural architecture search},
keywords = {Meta-heuristic},
title = {A holistic approach for resource-constrained neural network architecture search},
doi = {10.1016/j.asoc.2025.112832},
author = {Lupión, Marcos and Calvo Cruz, Nicolás and Martínez Ortigosa, Eva and Martínez Ortigosa, Pilar},
}