Trade-off Between Accuracy and Computational Cost With Neural Architecture Search: A Novel Strategy for Tactile Sensing Design

This letter presents a neural architecture search to optimize tactile elaboration systems taking into account the computational cost of the whole pipeline consisting of data preprocessing and a convolutional neural network (CNN) model to extract information. The strategy is exploited to train standard 1-D CNNs and binary CNNs on a three-class touch modality classification dataset. The experimental results show that systems based on standard CNNs outperform state-of-the-art techniques in terms of accuracy and computational cost, while the ones based on binary CNNs further reduce the computational cost with a small accuracy drop.

Automated summary

This letter introduces a neural architecture search method to optimize tactile elaboration systems, considering the computational cost of the entire pipeline including data preprocessing and a convolutional neural network (CNN) model for information extraction. The strategy is applied to train standard 1-D CNNs and binary CNNs on a three-class touch modality classification dataset. Experimental results show that systems based on standard CNNs outperform state-of-the-art techniques in terms of accuracy and computational cost, while those based on binary CNNs further reduce computational cost with a slight accuracy drop.