MorphBungee: A 65nm 7.2mm 2 27μJ/image Digital Edge Neuromorphic Chip with On-Chip 802 Frame/s Multi-Layer Spiking Neural Network Learning.
2023 IEEE Asian Solid-State Circuits Conference (A-SSCC)(2023)
Abstract
The spiking neural network (SNN) and event-driven neuromorphic architectures have gaining ever increasing popularity in low-cost and energy-efficient edge intelligent systems, as they closely mimic the human brain mechanism by utilizing spatiotemporally sparse binary spikes to represent and process sensory information in the neurons [1]. Especially, the small-scale digital ones attract more interests for their wide deployment potential in versatile edge-node applications such as wearables, drones and mobile platforms where cost, energy and latency budgets are strictly constrained [2]–[6]. However, many edge neuromorphic chips can only run shallow SNNs, leading to low object recognition accuracies. Moreover, they provide no or just single-layer on-chip learning function, failing to smartly and quickly adapt to the ever changing environment.
MoreTranslated text
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined