A Lightweight Multidendritic Pyramidal Neuron Model With Neural Plasticity on Image Recognition
Yu Zhang, Pengxing Cai, Yanan Sun, Zhiming Zhang, Zhenyu Lei, Shangce Gao
Abstract
Simulating the method of neurons in the human brain that process signals is crucial for constructing a neural network with biological interpretability. However, existing deep neural networks simplify the function of a single neuron without considering dendritic plasticity. In this paper, we present a multi-dendrite pyramidal neuron model (MDPN) for image classification, which mimics the multilevel dendritic structure of a nerve cell. Unlike the traditional feedforward network model, MDPN discards premature linear summation integration and employs a nonlinear dendritic computation such that improving the neuroplasticity. To model a lightweight and effective classification system, we emphasized the importance of single neuron and redefined the function of each subcomponent. Experimental results verify the effectiveness and robustness of our proposed MDPN in classifying 16 standardized image datasets with different characteristics. Compared to other state-of-the-art and well-known networks, MDPN is superior in terms of classification accuracy. The MDPN code is available on GitHub: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/zy-251026/MDPN</uri> .