Direct CMOS Implementation of Neuromorphic Temporal Neural Networks for Sensory Processing
Abstract
Temporal Neural Networks (TNNs) use time as a resource to represent and process information, mimicking the behavior of the mammalian neocortex. This work focuses on implementing TNNs using off-the-shelf digital CMOS technology. A microarchitecture framework is introduced with a hierarchy of building blocks including: multi-neuron columns, multi-column layers, and multi-layer TNNs. We present the direct CMOS gate-level implementation of the multi-neuron column model as the key building block for TNNs. Post-synthesis results are obtained using Synopsys tools and the 45 nm CMOS standard cell library. The TNN microarchitecture framework is embodied in a set of characteristic equations for assessing the total gate count, die area, compute time, and power consumption for any TNN design. We develop a multi-layer TNN prototype of 32M gates. In 7 nm CMOS process, it consumes only 1.54 mm^2 die area and 7.26 mW power and can process 28x28 images at 107M FPS (9.34 ns per image). We evaluate the prototype's performance and complexity relative to a recent state-of-the-art TNN model.
- Publication:
-
arXiv e-prints
- Pub Date:
- August 2020
- DOI:
- 10.48550/arXiv.2009.00457
- arXiv:
- arXiv:2009.00457
- Bibcode:
- 2020arXiv200900457N
- Keywords:
-
- Computer Science - Hardware Architecture;
- Computer Science - Emerging Technologies;
- Computer Science - Machine Learning;
- Computer Science - Neural and Evolutionary Computing
- E-Print:
- Submission Under Review for an IEEE Conference