Spiking neural networks (SNNs), a brain-inspired computing paradigm, are emerging for their inference performance, particularly in terms of energy efficiency and latency attributed to the plasticity in signal processing. To deploy SNNs in ubiquitous computing systems, signal encoding of sensors is crucial for achieving high accuracy and robustness. Using inertial sensor readings for gym activity recognition as a case study, this work comprehensively evaluates four main encoding schemes and deploys the corresponding SNN on the neuromorphic processor Loihi2 for post-deployment encoding assessment. Rate encoding, time-to-first-spike encoding, binary encoding, and delta modulation are evaluated using metrics like average fire rate, signal-to-noise ratio, classification accuracy, robustness, and inference latency and energy. In this case study, the time-to-first-spike encoding required the lowest firing rate (2%) and achieved a comparative accuracy (89%), although it was the least robust scheme against error spikes (over 20% accuracy drop with 0.1 noisy spike rate). Rate encoding with optimal value-to-probability mapping achieved the highest accuracy (91.7%). Binary encoding provided a balance between information reconstruction and noise resistance. Multi-threshold delta modulation showed the best robustness, with only a 0.7% accuracy drop at a 0.1 noisy spike rate. This work serves researchers in selecting the best encoding scheme for SNN-based ubiquitous sensor signal processing, tailored to specific performance requirements.
Invariant neuromorphic representations of tactile stimuli improve robustness of a real-time texture classification system
Johns Hopkins School of Medicine(约翰斯·霍普金斯医学院);University of Chicago(芝加哥大学);National Institutes of Health(美国国立卫生研究院);Vanderbilt University(范德堡大学);Johns Hopkins University(约翰斯·霍普金斯大学);The University of North Texas Health Science Center(北得克萨斯健康科学中心大学);Infinite Biomedical Technologies, LLC.(无限生物医学技术有限责任公司)
Integration of Contrastive Predictive Coding and Spiking Neural Networks
Université Paris-Saclay(巴黎萨克雷大学);İstanbul Teknik Üniversitesi(伊斯坦布尔技术大学);Osmaniye Korkut Ata Üniversitesi(奥斯曼耶·科鲁特阿大学);Erzincan Binali Yıldırım Üniversitesi(埃尔津詹·比纳利·伊利德里姆大学);Hacettepe Üniversitesi(哈恰特佩大学)
Vibe2Spike: Batteryless Wireless Tags for Vibration Sensing with Event Cameras and Spiking Networks
Department of EECS, The University of Tennessee, Knoxville(电子工程与计算机科学系,田纳西大学);Department of ECE, Oklahoma State University(电气与计算机工程系,俄克拉荷马州立大学);Accenture Labs, Accenture(Accenture实验室,Accenture)
Vibe2Spike 提出一种无电池无线振动感知框架,利用压电片、齐纳二极管和 LED 组成的超低成本标签采集振动能量并发射可见光脉冲,结合事件相机与演化优化的脉冲神经网络实现活动识别,在五类设备上达到 94.9% 的平均分类适应度。