Neuromorphic Computing

• Biological inspiration：spiking neurons、synaptic plasticity、temporal coding
• Spiking neural networks（SNNs）：integrate-and-fire models（LIF、IF）、spike timing
• Learning in SNNs：STDP（spike-timing-dependent plasticity）、surrogate gradient methods、从 ANNs 转换
• Neuromorphic hardware：Intel Loihi 2、IBM TrueNorth、SpiNNaker、BrainScaleS
• Event-driven computation：asynchronous processing、energy efficiency
• Event cameras（DVS）：neuromorphic vision sensors、sparse temporal data
• Applications：low-power edge inference、robotics、always-on sensing
• 与 conventional deep learning 的对比：latency、power、accuracy 的 tradeoffs