Decision-Tree-Initialized Dendritic Neuron Model for Fast and Accurate Data Classification

• Published in: IEEE transaction on neural networks and learning systems Vol. 33; no. 9; pp. 4173 - 4183
• Main Authors: Luo, Xudong, Wen, Xiaohao, Zhou, MengChu, Abusorrah, Abdullah, Huang, Lukui
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Algorithms; Back propagation networks; Biological neural networks; Biomembranes; Classification; Computational modeling; decision tree (DT); Decision trees; Dendrites; dendritic neuron model (DNM); Dendritic structure; machine learning; neural network; Neural networks; Neurons; Sparse matrices; Support vector machines; Synapses; Training

This work proposes a decision tree (DT)-based method for initializing a dendritic neuron model (DNM). Neural networks become larger and larger, thus consuming more and more computing resources. This calls for a strong need to prune neurons that do not contribute much to their network's output....