# Bridging LSTM Architecture and the Neural Dynamics during Reading

arXiv: https://arxiv.org/abs/1604.06635 · HTML: https://mlsanity.com/paper/1604.06635/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2016.

## Built on by (most cited first, 4 of 4)

- [Toward a realistic model of speech processing in the brain with self-supervised learning](https://mlsanity.com/paper/2206.01685/) (2022)
- [Mapping Brains with Language Models: A Survey](https://mlsanity.com/paper/2306.05126/) (2023)
- [Deep Learning Models to Study Sentence Comprehension in the Human Brain](https://mlsanity.com/paper/2301.06340/) (2023)
- [MEG-MASC: a high-quality magneto-encephalography dataset for evaluating natural speech processing](https://mlsanity.com/paper/2208.11488/) (2022)

## Abstract (arXiv)

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.