AUTHOR=Mo Lingfei , Wang Gang , Long Erhong , Zhuo Mingsong 

TITLE=ALSA: Associative Learning Based Supervised Learning Algorithm for SNN

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2022.838832

DOI=10.3389/fnins.2022.838832

ISSN=1662-453X

ABSTRACT=SNN (spiking neural network) is considered to be the brain-like model that best conforms to the biological mechanism of the brain. Due to the non-differentiability of spike, the training method of SNN is still not complete. This paper proposes a supervised learning method of SNN based on associative learning: ALSA. The method is based on the associative learning mechanism, and its realization process is similar to the animal conditioned reflex process, with strong physiological plausibility and rationality. This method uses improved spike timing-dependent plasticity (STDP) rules, combined with a teacher layer to induct spikes of neurons, to strengthen synaptic connections between input spike patterns and specified output neurons, and weaken synaptic connections between unrelated patterns and unrelated output neurons. Based on ALSA, this paper also completed the supervised learning classification tasks of the IRIS dataset and the MNIST dataset, and achieved 95.7% and 91.58% recognition accuracy respectively, which fully proves that ALSA is a feasible SNN supervised learning method. The innovation of this paper is to establish a biological plausible supervised learning method for SNN, which is based on the STDP learning rules and the associative learning mechanism that exists widely in animal training.