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 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.
Highlights
An important source of that inefficiency is a lack of specialization of computing systems for solving specific tasks, such as Artificial Intelligence (AI) problems
Based on the reentry paradigm, we have previously proposed the Reentrant Self-Organizing Maps (SOM) (ReSOM) model (Khacef et al, 2020b), a self-organizing artificial neural network based on local plasticity mechanisms for unsupervised learning and multimodal association (Khacef, 2020)
In order to overcome this limit, we proposed in Rodriguez et al (2018) to distribute the SOM computing based on the Iterative Grid (IG), a cellular neuromorphic architecture with local connectivity amongst neighbor neurons
Summary
The best example of an effective system for solving equivalent problems is the human brain Unlike their electronic counterparts, biological neurons use direct neural connections organized in a complex three dimensional structure. It offers universal computation capabilities and has technical and intellectual constraints, mainly because of the physical separation between memory and computation units This observation led us to develop a new computational paradigm combined with new electronic devices that support specialized neural models. Both are inspired by the selforganization property of the cortical areas of the biological brain, and their ability to learn their structure and function in an unsupervised manner while simultaneously acquiring data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
