Bridging LSTM Architecture and the Neural Dynamics during Reading
Authors: Peng Qian, Xipeng Qiu, Xuanjing Huang
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this paper, we study the cognitive plausibility of LSTM by aligning its internal architecture with the brain activity observed via f MRI when the subjects read a story. Experiment results show that the artiļ¬cial 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. |
| Researcher Affiliation | Academia | Peng Qian Xipeng Qiu Xuanjing Huang Shanghai Key Laboratory of Intelligent Information Processing, Fudan University School of Computer Science, Fudan University 825 Zhangheng Road, Shanghai, China {pqian11, xpqiu, xjhuang}@fudan.edu.cn |
| Pseudocode | No | The paper presents mathematical equations for LSTM unit states but does not include pseudocode or an algorithm block. |
| Open Source Code | No | The paper does not provide any links to its own source code or state that the code for its methodology is openly available. |
| Open Datasets | Yes | The brain imaging data is originally acquired in [Wehbe et al., 2014a], which recorded the brain activities of 8 subjects when they read the ninth chapter from the famous novel, Harry Porter and the Philosopher s Stone [Rowling, 1997]. ... Since only one chapter of Harry Porter and the Philosopher s Stone is involved in the original story reading experiment, the remaining chapters of the book is used as the training data. |
| Dataset Splits | Yes | We train the linear map model over about 95% of the brain imaging data and test the model over the remaining 5%. We apply 20-folds cross-validation in order to get the average performance of the model. |
| Hardware Specification | No | The paper describes the fMRI equipment used for data acquisition ('functional Magnetic Resonance Imaging (f MRI)') but does not specify the computing hardware (e.g., GPU, CPU models, memory) used for training or running their LSTM models. |
| Software Dependencies | No | The paper mentions software components like 'LSTM neural network', 'recurrent neural network', 'tf-idf', and 'word embeddings' (referencing a 'public Turian word embedding dataset') but does not provide specific version numbers for any software libraries, frameworks, or languages used. |
| Experiment Setup | Yes | In our experiments, the dimensionality of word embeddings is set to 50, the hidden state size is also set to 50, and the initial learning rate is set to 0.1. The other parameters are initialized by randomly sampling from uniform distribution in [-0.1, 0.1], based on the experience with recurrent neural network. |