A survey on dendritic neuron model: Mechanisms, algorithms and practical applications

Abstract

Research on dendrites has been conducted for decades, providing valuable information for the development of dendritic computation. Creating an ideal neuron model is crucial for computer science and may also provide robust guidance for understanding our brain’s underlying mechanisms and principles. This paper aims to review the related studies regarding a newly emerging, non-spiking and biologically inspired model, the dendritic neuron model (DNM). By mimicking the biological phenomena of neurons in vivo, the DNM incorporates a neural pruning scheme to eliminate superfluous synapses and dendrites, simplifying its architecture and forming unique neuron morphology for a specific task. Furthermore, the simplified structure can be transformed into logic circuits consisting of the comparators and logic AND, OR and NOT gates, without sacrificing model accuracy. The rapidity of binary operations in hardware implementation gives the DNM a distinct advantage to handle high-speed data streams. The advent of the big data era has led to an exponential explosion in the amount and variety of available information. The appealing properties of the DNM lead us to believe that it is worthy of more attention and that it might be a promising data mining technique. This article presents an in-depth analysis of the pruning and transformation mechanisms and a comprehensive review of the learning algorithms and real-world applications of the DNM. It also presents an empirical comparison of the optimization performance of different algorithms. Finally, we outline some critical issues and future works of the DNM. All the source code of DNM is available at http://www.dnm.net.cn/.