6 papers · 1 filter
Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment
Chengting Yu, Xiaochen Zhao, Lei Liu +4
Spiking Neural Networks (SNNs) are emerging as a brain-inspired alternative to traditional Artificial Neural Networks (ANNs), prized for their potential energy efficiency on neurom…
Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement
Shu Yang, Chengting Yu, Lei Liu +3
Spiking Neural Networks (SNNs) have garnered considerable attention as a potential alternative to Artificial Neural Networks (ANNs). Recent studies have highlighted SNNs' potential…
Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart
Chengting Yu, Shu Yang, Fengzhao Zhang +3
Quantization-aware training (QAT) is a common paradigm for network quantization, in which the training phase incorporates the simulation of the low-precision computation to optimiz…
Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment
Chengting Yu, Fengzhao Zhang, Ruizhe Chen +4
Knowledge Distillation (KD), a learning manner with a larger teacher network guiding a smaller student network, transfers dark knowledge from the teacher to the student via logits…
Go beyond End-to-End Training: Boosting Greedy Local Learning with Context Supply
Chengting Yu, Fengzhao Zhang, Hanzhi Ma +2
Traditional end-to-end (E2E) training of deep networks necessitates storing intermediate activations for back-propagation, resulting in a large memory footprint on GPUs and restric…
Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation
Chengting Yu, Lei Liu, Gaoang Wang +2
Recent insights have revealed that rate-coding is a primary form of information representation captured by surrogate-gradient-based Backpropagation Through Time (BPTT) in training…