An optimized Hebbian Learning Rule for Spiking Neural Networks on the Classification Problems with Informative Data Features
- Resource Type
- Conference
- Authors
- Chen, Tingyu; Hu, Xin; Zhou, Yiren; Zou, Zhuo; Liang, Longfei; Yang, Wen-Chi
- Source
- 2022 Asia Conference on Advanced Robotics, Automation, and Control Engineering (ARACE) ARACE Advanced Robotics, Automation, and Control Engineering (ARACE), 2022 Asia Conference on. :18-23 Aug, 2022
- Subject
- Computing and Processing
Training
Machine learning algorithms
Neurons
Mathematical models
Computational efficiency
Classification algorithms
Hebbian theory
Neural Network Theory and Architectures
Spiking Neural Network
Unsupervised and Supervised Learning
Performance analysis of Machine Learning Algorithms
- Language
We proposed a new Hebbian learning rule that Neglects Historical data and only Compares Voltages (referred to NHCV in the paper). Unlike the traditional Hebbian learning rules that rely on comparing the spike timing, NHCV is designed to adjust the weight of the synapse based on the voltage of the neuron as soon as it fires. NHCV is computationally efficient and have advantages in processing informative features. Compared to traditional STDP learning rules, it accelerated training process (0.5 to 2 seconds improvement on each sample) and achieved better accuracy on Wine dataset (5.7% absolute improvement) and Diabetes dataset (12% absolute improvement). We reveal that the information amount inside the features of a dataset considerably affects the performance of SNNs.