Skip to Main content Skip to Navigation
Conference papers

Real-Time Multi-board Architecture for Analog Spiking Neural Networks

Abstract : In this paper, we present a multi-board system based on analog neuromimetic ICs. These ICs compute in realtime conductance-based models. These models are implemented in a modular architecture based on our analog IPs. Each IC includes five neurons and analog memory cells to set and store the conductance model parameters, and eventually optimize it to compensate the analog circuit variability. The circuits are embedded in a multi-board system able to host up to 120 neurons spread across 6 boards all connected to a backplane with daisy-chain facilities. Each action potential computed by analog neuromimetic chips is time-stamped when detected by digital device (FPGA). These FPGAs are also in charge of the real-time plasticity computation and of controlling inter-boards communication. The system is designed to compute programmable models and connectivity schemes.
Document type :
Conference papers
Complete list of metadatas
Contributor : Chrystel Plumejeau <>
Submitted on : Friday, July 23, 2010 - 11:57:55 AM
Last modification on : Thursday, January 11, 2018 - 6:21:06 AM


  • HAL Id : hal-00505314, version 1


S. Saïghi, J. Tomas, Y. Bornat, B. Belhadj, O. Malot, et al.. Real-Time Multi-board Architecture for Analog Spiking Neural Networks. ISCAS 2010, May 2010, Paris, France. pp.1939-1942. ⟨hal-00505314⟩



Record views