Bridging LSTM Architecture and the Neural Dynamics during Reading

04/22/2016
by   Peng Qian, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 6

05/06/2016

LSTM with Working Memory

Previous RNN architectures have largely been superseded by LSTM, or "Lon...
10/14/2020

From Language to Language-ish: How Brain-Like is an LSTM's Representation of Nonsensical Language Stimuli?

The representations generated by many models of language (word embedding...
09/10/2017

Cognitive networks: brains, internet, and civilizations

In this short essay, we discuss some basic features of cognitive activit...
10/23/2018

Interpretable LSTMs For Whole-Brain Neuroimaging Analyses

The analysis of neuroimaging data poses several strong challenges, in pa...
02/04/2014

Cognitive Aging as Interplay between Hebbian Learning and Criticality

Cognitive ageing seems to be a story of global degradation. As one ages ...
06/24/2019

Inverse reinforcement learning conditioned on brain scan

We outline a way for an agent to learn the dispositions of a particular ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.