FeFET-Based Neuromorphic Architecture with On-Device Feedback Alignment Training

Abstract

With the onset of on-device learning in neuromorphic systems, there are a requisition for compute-lite learning rules and novel emerging devices that address the memory bottleneck. In this research, we propose a neuromorphic architecture with FeFET synapse arrays and study the efficacy of write schemes for feedback alignment backpropagation algorithm. The proposed architecture is benchmarked for two write programming schemes, sawtooth pulse and incremental pulse. The sawtooth write programming scheme is further simplified for resource efficient training, by sharing the pulse generator with local control circuitry across multiple neurons. When the overall architecture is benchmarked for on-device learning, we observed that both writing schemes result in comparable performance, but the sawtooth is more efficient in terms of power consumption and area.