paper-with-me

홈 › Papers

Bridging LSTM Architecture and the Neural Dynamics during Reading

2016-04-22 · Peng Qian, Xipeng Qiu, Xuanjing Huang

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.

📄 PDF Abstract BibTeX arXiv:1604.06635

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference

2018-02-15 · NAACL 2018 6 · Reza Ghaeini, Sadid A. Hasan, Vivek Datla, Joey Liu 외

We present a novel deep learning architecture to address the natural language inference (NLI) task. Existing approaches mostly rely on simple reading mechanisms for independent encoding of the premise and hypothesis. Ins…

Natural Language Inference

Minimal Convolutional RNNs Accelerate Spatiotemporal Learning

2025-08-05 · Coşku Can Horuz, Sebastian Otte, Martin V. Butz, Matthias Karlbauer arxiv

We introduce MinConvLSTM and MinConvGRU, two novel spatiotemporal models that combine the spatial inductive biases of convolutional recurrent networks with the training efficiency of minimal, parallelizable RNNs. Our app…

Neural Speed Reading with Structural-Jump-LSTM

2019-03-20 · ICLR 2019 5 · Christian Hansen, Casper Hansen, Stephen Alstrup, Jakob Grue Simonsen 외

Recurrent neural networks (RNNs) can model natural language by sequentially 'reading' input tokens and outputting a distributed representation of each token. Due to the sequential nature of RNNs, inference time is linear…

Sentence

LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models

2019-06-25 · Dilip Kumar Margam, Rohith Aralikatti, Tanay Sharma, Abhinav Thanda 외

In recent years, deep learning based machine lipreading has gained prominence. To this end, several architectures such as LipNet, LCANet and others have been proposed which perform extremely well compared to traditional …

Lipreading

Bridging Information-Seeking Human Gaze and Machine Reading Comprehension

2020-09-30 · CONLL 2020 · Jonathan Malmaud, Roger Levy, Yevgeni Berzak

In this work, we analyze how human gaze during reading comprehension is conditioned on the given reading comprehension question, and whether this signal can be beneficial for machine reading comprehension. To this end, w…

Machine Reading ComprehensionMultiple-choiceQuestion AnsweringReading Comprehension