Knowledge Discovery from Layered Neural Networks Based on Non-negative Task Matrix Decomposition

Chihiro WATANABE  Kaoru HIRAMATSU  Kunio KASHINO  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E103-D   No.2   pp.390-397
Publication Date: 2020/02/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2019EDP7136
Type of Manuscript: PAPER
Category: Artificial Intelligence, Data Mining
Keyword: 
interpretable machine learning,  neural networks,  non-negative matrix factorization,  clustering,  

Full Text: PDF(1.4MB)>>
Buy this Article




Summary: 
Interpretability has become an important issue in the machine learning field, along with the success of layered neural networks in various practical tasks. Since a trained layered neural network consists of a complex nonlinear relationship between large number of parameters, we failed to understand how they could achieve input-output mappings with a given data set. In this paper, we propose the non-negative task matrix decomposition method, which applies non-negative matrix factorization to a trained layered neural network. This enables us to decompose the inference mechanism of a trained layered neural network into multiple principal tasks of input-output mapping, and reveal the roles of hidden units in terms of their contribution to each principal task.