A unified software/hardware scalable architecture for brain-inspired computing based on self-organizing neural models

Abstract

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 an original 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.

Self-organization of an inhomogeneous memristive hardware for sequence learning

“…Unsupervised self-organizing networks have been previously studied on different hardware substrates, such as Self-organizing Maps (SOM) on Field Programmable Gate Array (FPGA) 39 , and reservoir computing using nano-wire networks 40,41 .…”

“…The FPGA substrate was used to implement SOMs for multi-modal sensory processing 39 . Hebbian learning was employed to create the SOM in each map, by calculating the weight update based on the input signal.…”