Dendritic Branches of DNM Help to Improve Approximation accuracy
暂无分享,去创建一个
This paper rigorously establishes that, by increasing the number of dendritic branches, we can achieve an infinite approximation to any continuous function with any accuracy. In other words, the accuracy can be improved by using one neuron with more dendritic branches under the premise of using the backpropagation neural network theory.