Skip to Main Content
The design of systems to replicate complex neural functionality is a requirement for the development of next-generation prosthetic devices. The demands of such neural models are growing exponentially as we discover more about how brain systems function. It is therefore important for the electronic architectures involved to scale effectively in terms of latency, area and power usage in order to be able to process more advanced neural models. Within this paper a design is proposed that utilises the parallel nature and the resources available upon modern FPGAs to achieve a scalable and efficient method for the implementation of complex neural models, allowing for the simulation of 150000 ion channels concurrently.
Date of Conference: 29-31 Aug. 2012