Bridging LSTM Architecture and the Neural Dynamics during Reading
Abstract
Recently, the long short-term memory neural network (LSTM) has attracted wide interest due to its success in many tasks. LSTM architecture consists of a memory cell and three gates, which looks similar to the neuronal networks in the brain. However, there still lacks the evidence of the cognitive plausibility of LSTM architecture as well as its working mechanism. In this paper, we study the cognitive plausibility of LSTM by aligning its internal architecture with the brain activity observed via fMRI when the subjects read a story. Experiment results show that the artificial memory vector in LSTM can accurately predict the observed sequential brain activities, indicating the correlation between LSTM architecture and the cognitive process of story reading.
Cite
@article{arxiv.1604.06635,
title = {Bridging LSTM Architecture and the Neural Dynamics during Reading},
author = {Peng Qian and Xipeng Qiu and Xuanjing Huang},
journal= {arXiv preprint arXiv:1604.06635},
year = {2016}
}
Comments
25th International Joint Conference on Artificial Intelligence IJCAI-16