Title: Construction of Subject-independent Brain Decoders for Human FMRI with Deep Learning

Year of Publication: Nov - 2014
Page Numbers: 60-68
Authors: Sotetsu Koyamada, Yumi Shikauchi, Ken Nakae, Shin Ishii
Conference Name: The International Conference on Data Mining, Internet Computing, and Big Data (BigData2014)
- Malaysia

Abstract:


Brain decoding, to decode a stimulus given to or a mental state of human participants from measurable brain activities by means of machine learning techniques, has made a great success in recent years. Due to large variation of brain activities between individuals, however, previous brain decoding studies mostly put focus on developing an individual-specific decoder. For making brain decoding more applicable for practical use, in this study, we explored to build an individualindependent decoder with a large-scale functional magnetic resonance imaging (fMRI) database. We constructed the decoder by deep neural network learning, which is the most successful technique recently developed in the field of data mining. Our decoder achieved the higher decoding accuracy than other baseline methods like support vector machine (SVM). Furthermore, increasing the number of subjects for training led to higher decoding accuracy, as expected. These results show that the deep neural networks trained by large-scale fMRI databases are useful for construction of individual-independent decoders and for their applications for practical use.