Fast Learning Architecture for Neural Networks

Ming Jun Zhang (1) , Samuel Garcia (1) , Michel Terre (1)

1 CEDRIC - LAETITIA - CEDRIC. Traitement du signal et architectures électroniques

This paper proposes a solution to minimize the learning time of a fully connected neural network. The paper presents a processing architecture in which the treatments applied to the examples of the learning base are strongly parallelized and anticipated, even before the parameters adaptation of the previous examples are completed. This strategy finally leads to a delayed adaptation and the impact of this delay on the learning performances is analysed through a simple replicable school case study. It is shown that a reduction of the adaptation step size could be proposed to compensate errors due to the delayed adaptation. Finally, the gain in processing time for the learning phase is analysed as a function of the network parameters chosen in this study.

Mots clés: Neural networks; Learning algorithms; Architecture; FPGA

Domaines: Sciences de l'ingénieur [physics]

Ming Jun Zhang, Samuel Garcia, Michel Terre. Fast Learning Architecture for Neural Networks. 2022 30th European Signal Processing Conference (EUSIPCO), Aug 2022, Belgrade, Serbia. pp.1611-1615, ⟨10.23919/EUSIPCO55093.2022.9909812⟩. ⟨hal-03956819⟩