Presentation information

Oral presentation

General Session » [General Session] 13. AI Application

[2J4] [General Session] 13. AI Application

Wed. Jun 6, 2018 5:20 PM - 6:40 PM Room J (2F Royal Garden B)

座長:小澤 順(産業技術総合研究所)

5:40 PM - 6:00 PM

[2J4-02] Feature selection and over-adaptation prevention in neural networks using the auxiliary weight method

〇Akira NODA1 (1. Technology Research Laboratory, Shimadzu Corp.)

Keywords:Neuralnetwork, Feature extraction, Over-adaptation, Mass spectrometry, Disease diagnosis

In this study, we propose a method called auxiliary weight (AW) for neural networks in which each input value is weighted according to its contribution to the input dimension. AW is similar to Lasso regularization in the sense that it can extract features; however, AW is faster than Lasso in processing data that contains a several contributing dimensions and massive non-contributing dimensions, such as the data of medical mass spectrometry.