题目/Title：ANP-G: A 28nm 1.04pJ/SOP Sub-mm2 Spiking and Back-propagation Hybrid Neural Network Asynchronous Olfactory Processor Enabling Few-shot Class-incremental On-chip Learning

作者/Author：
                        Dexuan Huo, Jilin Zhang, Xinyu Dai, Jian Zhang, Chunqi Qian, Kea-Tiong Tang, Hong Chen

会议/Conference：VLSI Technology and Circuits 2023

地点/Location：Kyoto, Japan

年份/Issue Date：2023.11-16 Jun.

页码/pages：pp.1-2

摘要/Abstract：

This paper presents a 28nm 1.04pJ/SOP sub-mm2 spiking and back-propagation hybrid neural network asynchronous olfactory processor enabling few-shot class-incremental on-chip learning for the first time, showing <33.27渭W training power budget at 0.55V with gas recognition, concentration estimation, and gas incremental learning tasks. This processor achieves 110.62脳 and 4.09脳 energy saving respectively over the state-of-the-art gas recognition and SNN chips.