7 papers
Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks
Zhuobin Yang, Yeyao Bao, Liangfu Lv +3
Spiking Neural Networks (SNNs) are promising for energy-efficient, real-time edge computing, yet their performance is often constrained by the limited adaptability of conventional…
CDRL: A Reinforcement Learning Framework Inspired by Cerebellar Circuits and Dendritic Computational Strategies
Sibo Zhang, Rui Jing, Liangfu Lv +2
Reinforcement learning (RL) has achieved notable performance in high-dimensional sequential decision-making tasks, yet remains limited by low sample efficiency, sensitivity to nois…
Seemingly Redundant Modules Enhance Robust Odor Learning in Fruit Flies
Haiyang Li, Liao Yu, Qiang Yu +1
Biological circuits have evolved to incorporate multiple modules that perform similar functions. In the fly olfactory circuit, both lateral inhibition (LI) and neuronal spike frequ…
FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
Heming Zou, Yunliang Zang, Wutong Xu +2
Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for foundation models, but it suffers from parameter interference, resulting in suboptimal perfor…
Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning
Heming Zou, Yunliang Zang, Wutong Xu +1
Using a nearly-frozen pretrained model, the continual representation learning paradigm reframes parameter updates as a similarity-matching problem to mitigate catastrophic forgetti…
NSPDI-SNN: An efficient lightweight SNN based on nonlinear synaptic pruning and dendritic integration
Wuque Cai, Hongze Sun, Jiayi He +5
Spiking neural networks (SNNs) are artificial neural networks based on simulated biological neurons and have attracted much attention in recent artificial intelligence technology s…