Neuromorphic Computing
Neuromorphic computing aims to build energy-efficient computer systems inspired by the brain's architecture, focusing on spiking neural networks (SNNs) that process information via brief electrical pulses. Current research emphasizes improving SNN training methods, particularly addressing challenges in deep network architectures and exploring novel algorithms like surrogate gradients and online learning rules to enhance accuracy and reduce power consumption. This field holds significant promise for advancing artificial intelligence, particularly in resource-constrained applications like robotics and edge computing, by offering substantial improvements in energy efficiency and processing speed compared to traditional computing.
Papers
Efficient Speech Command Recognition Leveraging Spiking Neural Network and Curriculum Learning-based Knowledge Distillation
Jiaqi Wang, Liutao Yu, Liwei Huang, Chenlin Zhou, Han Zhang, Zhenxi Song, Min Zhang, Zhengyu Ma, Zhiguo Zhang
ALADE-SNN: Adaptive Logit Alignment in Dynamically Expandable Spiking Neural Networks for Class Incremental Learning
Wenyao Ni, Jiangrong Shen, Qi Xu, Huajin Tang
SpikeAtConv: An Integrated Spiking-Convolutional Attention Architecture for Energy-Efficient Neuromorphic Vision Processing
Wangdan Liao, Weidong Wang
A High Energy-Efficiency Multi-core Neuromorphic Architecture for Deep SNN Training
Mingjing Li, Huihui Zhou, Xiaofeng Xu, Zhiwei Zhong, Puli Quan, Xueke Zhu, Yanyu Lin, Wenjie Lin, Hongyu Guo, Junchao Zhang, Yunhao Ma, Wei Wang, Qingyan Meng, Zhengyu Ma, Guoqi Li, Xiaoxin Cui, Yonghong Tian