Visible to the public Estimating the Number of Hidden Nodes of the Single-Hidden-Layer Feedforward Neural Networks

TitleEstimating the Number of Hidden Nodes of the Single-Hidden-Layer Feedforward Neural Networks
Publication TypeConference Paper
Year of Publication2019
AuthorsCai, Guang-Wei, Fang, Zhi, Chen, Yue-Feng
Conference Name2019 15th International Conference on Computational Intelligence and Security (CIS)
Date Published05 March 2020
ISBN Number978-1-7281-6092-4
KeywordsArtificial neural networks, attribute-based data normalization, compositionality, Computer architecture, cyber physical systems, data normalization, decomposition, Eigenvalues and eigenfunctions, feedforward neural nets, Feedforward neural networks, hidden nodes, Metrics, normalized data, optimal number, pubcrawl, sample-based data normalization, single-hidden-layer feedforward neural network, singular value decomposition, Training, Training data

In order to solve the problem that there is no effective means to find the optimal number of hidden nodes of single-hidden-layer feedforward neural network, in this paper, a method will be introduced to solve it effectively by using singular value decomposition. First, the training data need to be normalized strictly by attribute-based data normalization and sample-based data normalization. Then, the normalized data is decomposed based on the singular value decomposition, and the number of hidden nodes is determined according to main eigenvalues. The experimental results of MNIST data set and APS data set show that the feedforward neural network can attain satisfactory performance in the classification task.

Citation Keycai_estimating_2019