Temperature-Resilient Analog Neuromorphic Chip in Single-Polysilicon CMOS Technology

TL;DR

This paper presents a temperature-resilient analog neuromorphic chip fabricated in single-poly CMOS technology, capable of accurate image classification across a wide temperature range by implementing a novel temperature compensation mechanism.

Contribution

The authors introduce a temperature compensation mechanism for analog neuromorphic circuits, enabling robust operation from 10°C to 60°C without accuracy loss.

Findings

Achieved temperature resilience with less than 2% accuracy deviation

Implemented a neural network in analog CMOS with unconventional NVMs

Demonstrated effective temperature compensation in hardware

Abstract

In analog neuromorphic chips, designers can embed computing primitives in the intrinsic physical properties of devices and circuits, heavily reducing device count and energy consumption, and enabling high parallelism, because all devices are computing simultaneously. Neural network parameters can be stored in local analog non-volatile memories (NVMs), saving the energy required to move data between memory and logic. However, the main drawback of analog sub-threshold electronic circuits is their dramatic temperature sensitivity. In this paper, we demonstrate that a temperature compensation mechanism can be devised to solve this problem. We have designed and fabricated a chip implementing a two-layer analog neural network trained to classify low-resolution images of handwritten digits with a low-cost single-poly complementary metal-oxide-semiconductor (CMOS) process, using unconventional analog NVMs for weight storage. We demonstrate a temperature-resilient analog neuromorphic chip for image recognition operating between 10$^{\circ}$C and 60$^{\circ}$C without loss of classification accuracy, within 2\% of the corresponding software-based neural network in the whole temperature range.