A Unified Software/Hardware Scalable Architecture for Brain-Inspired Computing Based on Self-Organizing Neural Models.

Autor:	Muliukov AR; Université Côte d'Azur, Laboratoire d'Electronique, Antennes et Télécommunications, CNRS, Biot, France., Rodriguez L; Université Côte d'Azur, Laboratoire d'Electronique, Antennes et Télécommunications, CNRS, Biot, France., Miramond B; Université Côte d'Azur, Laboratoire d'Electronique, Antennes et Télécommunications, CNRS, Biot, France., Khacef L; Bio-Inspired Circuits and Systems Lab, Zernike Institute for Advanced Materials, Groningen Cognitive Systems and Materials Center, University of Groningen, Groningen, Netherlands., Schmidt J; Institute of Information Technologies, Hepia, University of Applied Sciences and Arts of Western Switzerland, Geneva, Switzerland., Berthet Q; Institute of Information Technologies, Hepia, University of Applied Sciences and Arts of Western Switzerland, Geneva, Switzerland., Upegui A; Institute of Information Technologies, Hepia, University of Applied Sciences and Arts of Western Switzerland, Geneva, Switzerland.
Jazyk:	angličtina
Zdroj:	Frontiers in neuroscience [Front Neurosci] 2022 Mar 02; Vol. 16, pp. 825879. Date of Electronic Publication: 2022 Mar 02 (Print Publication: 2022).
DOI:	10.3389/fnins.2022.825879
Abstrakt:	The field of artificial intelligence has significantly advanced over the past decades, inspired by discoveries from the fields of biology and neuroscience. The idea of this work is inspired by the process of self-organization of cortical areas in the human brain from both afferent and lateral/internal connections. In this work, we develop a brain-inspired neural model associating Self-Organizing Maps (SOM) and Hebbian learning in the Reentrant SOM (ReSOM) model. The framework is applied to multimodal classification problems. Compared to existing methods based on unsupervised learning with post-labeling, the model enhances the state-of-the-art results. This work also demonstrates the distributed and scalable nature of the model through both simulation results and hardware execution on a dedicated FPGA-based platform named SCALP (Self-configurable 3D Cellular Adaptive Platform). SCALP boards can be interconnected in a modular way to support the structure of the neural model. Such a unified software and hardware approach enables the processing to be scaled and allows information from several modalities to be merged dynamically. The deployment on hardware boards provides performance results of parallel execution on several devices, with the communication between each board through dedicated serial links. The proposed unified architecture, composed of the ReSOM model and the SCALP hardware platform, demonstrates a significant increase in accuracy thanks to multimodal association, and a good trade-off between latency and power consumption compared to a centralized GPU implementation. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2022 Muliukov, Rodriguez, Miramond, Khacef, Schmidt, Berthet and Upegui.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu