Architectures for high-performance FPGA implementations of neural models

Journal of Neural Engineering
Randall K Weinstein, Robert H Lee

Abstract

As the complexity of neural models continues to increase (larger populations, varied ionic conductances, more detailed morphologies, etc) traditional software-based models have difficulty scaling to reach the performance levels desired. This paper describes the use of FPGAs, or field programmable gate arrays, to easily implement a wide variety of neural models with the performance of custom analogue circuits or computer clusters, the reconfigurability of software, and at a cost rivalling personal computers. FPGAs reach this level of performance by enabling the design of neural models as parallel processed data paths. These architectures provide for a wide range of single-compartment, multi-compartment and population models to be readily converted to FPGA implementations. Generalized architectures are described for the efficient modelling of a first-order, nonlinear differential equation in throughput maximizing or latency minimizing data-path configurations. The homogeneity of population and multicompartment models is exploited to form deep pipelines for improved performance. Limitations of FPGA architectures and future research areas are explored.

References

Dec 1, 1995·Journal of Computational Neuroscience·V Booth, J Rinzel
Jun 13, 2001·Tumori·J A Barbara
Sep 20, 2001·IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society·R JungJ J Abbas

❮ Previous
Next ❯

Citations

Sep 27, 2006·Neural Computation·Ruben Guerrero-RiveraTim C Pearce
May 1, 2009·HFSP Journal·Guy Rachmuth, Chi-Sang Poon
Jan 1, 2016·Medical & Biological Engineering & Computing·Peng LiShuenn-Yuh Lee
Sep 1, 2015·Neural Networks : the Official Journal of the International Neural Network Society·Shuangming YangHuiyan Li
Jul 1, 2008·IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society·Osbert C Zalay, Berj L Bardakjian
Apr 18, 2007·IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society·Randall K WeinsteinRobert H Lee
Dec 28, 2006·IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society·Terrence S T MakChi-Sang Poon
Jul 6, 2016·Frontiers in Neuroscience·Takashi KohnoKazuyuki Aihara
Jul 15, 2017·Journal of Neural Engineering·Georgios SmaragdosChristos Strydis
May 10, 2008·Minimally Invasive Therapy & Allied Technologies : MITAT : Official Journal of the Society for Minimally Invasive Therapy·Patrick WahlWilhelm Bloch

❮ Previous
Next ❯

Related Concepts

Related Feeds

Brain-Computer Interface

A brain-computer interface, also known as a brain-machine interface, is a bi-directional communication pathway between an external device and a wired brain. Here is the latest research on this topic.

© 2021 Meta ULC. All rights reserved