Braindrop: A Mixed-Signal Neuromorphic Architecture With a Dynamical Systems-Based Programming Model

Braindrop is the first neuromorphic system designed to be programmed at a high level of abstraction. Previous neuromorphic systems were programmed at the neurosynaptic level and required expert knowledge of the hardware to use. In stark contrast, Braindrop's computations are specified as couple...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the IEEE 2019-01, Vol.107 (1), p.144-164
Main Authors: Neckar, Alexander, Fok, Sam, Benjamin, Ben V., Stewart, Terrence C., Oza, Nick N., Voelker, Aaron R., Eliasmith, Chris, Manohar, Rajit, Boahen, Kwabena
Format: Article
Language:English
Subjects:
Analog circuits
Artificial neural networks
asynchronous circuits
Brain models
Computer architecture
Convolution
Decoding
Dynamical systems
Encoding
Hardware
Neuromorphics
Neurons
Nonlinear systems
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Braindrop is the first neuromorphic system designed to be programmed at a high level of abstraction. Previous neuromorphic systems were programmed at the neurosynaptic level and required expert knowledge of the hardware to use. In stark contrast, Braindrop's computations are specified as coupled nonlinear dynamical systems and synthesized to the hardware by an automated procedure. This procedure not only leverages Braindrop's fabric of subthreshold analog circuits as dynamic computational primitives but also compensates for their mismatched and temperature-sensitive responses at the network level. Thus, a clean abstraction is presented to the user. Fabricated in a 28-nm FDSOI process, Braindrop integrates 4096 neurons in 0.65 mm 2 . Two innovations-sparse encoding through analog spatial convolution and weighted spike-rate summation though digital accumulative thinning-cut digital traffic drastically, reducing the energy Braindrop consumes per equivalent synaptic operation to 381 fJ for typical network configurations.
ISSN:0018-9219
1558-2256
DOI:10.1109/JPROC.2018.2881432