Neural network with multiple connection weights
作者：
Highlights：
• Biological studies have shown that one neuron simultaneously releases different types ofneurotransmitters to another neuron for information transfer, of which different types of neurotransmitters play different roles. Motivated by this biological discovery, a novel neural networks with Multiple Connection Weights (MNN) is proposed.
• The greedy layer-by-layer pre-training method is proposed to pre-train MNN model.
• The universal approximation of MNN has been proved.
• The experimental results on MNIST, NORB and seven UCI datasets have been done and show that the performance of MNN outperformed the traditional neural network.
• The dimension expansion of weights provide new insights into structure design of the neural network model.
摘要
•Biological studies have shown that one neuron simultaneously releases different types ofneurotransmitters to another neuron for information transfer, of which different types of neurotransmitters play different roles. Motivated by this biological discovery, a novel neural networks with Multiple Connection Weights (MNN) is proposed.•The greedy layer-by-layer pre-training method is proposed to pre-train MNN model.•The universal approximation of MNN has been proved.•The experimental results on MNIST, NORB and seven UCI datasets have been done and show that the performance of MNN outperformed the traditional neural network.•The dimension expansion of weights provide new insights into structure design of the neural network model.
论文关键词：Neural network,Neurotransmitter,Interpretability,Extending dimension
论文评审过程：Received 17 October 2019, Revised 19 April 2020, Accepted 31 May 2020, Available online 2 June 2020, Version of Record 15 June 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107481
