Extending SpArSe: Automatic Gesture Recognition Architectures for Embedded Devices

Juan Borrego-Carazo, David Castells-Rufas, Jordi Carrabina, Ernesto Biempica

Producció científica: Capítol de llibreCapítolRecercaAvaluat per experts

Resum

Neural Architecture Search (NAS), which allows for automatically developing neural networks, has been mostly devoted to performance on a single metric, usually accuracy. New approaches have added more objectives, such as model size, in order to find networks suitable for resource-constrained platforms. SpArSe [1] is a multi-objective Bayesian optimization framework for automatically developing image classification convolutional neural networks (CNNs) for micro-controller units (MCUs). In this work, we first implement SpArSe and modify it to reduce search time, obtaining similar results regarding accuracy, model size, and maximum working memory but in less optimization time. Moreover, we extend the search space to include recurrent neural networks (RNNs) and add an inference latency objective for time-constrained tasks. Finally, we test our implementation in a gesture recognition task obtaining better results than previous manually tuned approaches for size and performance metrics, which validates the approach and its utility.

Idioma originalEnglish
Títol de la publicacióProceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020
EditorsM. Arif Wani, Feng Luo, Xiaolin Li, Dejing Dou, Francesco Bonchi
Pàgines7-12
Nombre de pàgines6
ISBN (electrònic)9781728184708
DOIs
Estat de la publicacióPublicada - de des. 2020

Sèrie de publicacions

NomProceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020

Fingerprint

Navegar pels temes de recerca de 'Extending SpArSe: Automatic Gesture Recognition Architectures for Embedded Devices'. Junts formen un fingerprint únic.

Com citar-ho