Linear Leaky-Integrate-and-Fire Neuron Model Based Spiking Neural Networks and Its Mapping Relationship to Deep Neural Networks
This provides a theoretical basis for combining the biological plausibility of SNNs with the efficiency of DNNs, addressing a foundational gap in brain-inspired machine learning.
The paper tackled the problem of lacking theoretical groundwork for training spiking neural networks (SNNs) without accuracy loss by establishing a precise mathematical mapping between Linear Leaky-Integrate-and-Fire (LIF) SNN parameters and ReLU-based deep neural network (DNN) parameters, which was analytically proven and demonstrated through simulations and real data experiments.
Spiking neural networks (SNNs) are brain-inspired machine learning algorithms with merits such as biological plausibility and unsupervised learning capability. Previous works have shown that converting Artificial Neural Networks (ANNs) into SNNs is a practical and efficient approach for implementing an SNN. However, the basic principle and theoretical groundwork are lacking for training a non-accuracy-loss SNN. This paper establishes a precise mathematical mapping between the biological parameters of the Linear Leaky-Integrate-and-Fire model (LIF)/SNNs and the parameters of ReLU-AN/Deep Neural Networks (DNNs). Such mapping relationship is analytically proven under certain conditions and demonstrated by simulation and real data experiments. It can serve as the theoretical basis for the potential combination of the respective merits of the two categories of neural networks.