Implementing Neural Models in Silicon

Abstract

Neural models are used in both computational neuroscience and in pattern recognition. The aim of the first is understanding of real neural systems, and of the second is gaining better, possibly brainlike performance for systems being built. In both cases, the highly parallel nature of the neural system contrasts with the sequential nature of computer systems, resulting in slow and complex simulation software. More direct implementation in hardware (whether digital or analogue) holds out the promise of faster emulation both because hardware implementation is inherently faster than software and the operation is much more parallel. There are costs to this: modifying the system (for example, to test out variants of the system) is much harder when a full application-specific integrated circuit has been built. Fast emulation can permit direct incorporation of a neural model into a system, permitting real-time input and output. Appropriate selection of implementation technology can help to make simplify interfacing the system to external devices. We review the technologies involved and discuss some example systems.