paper-with-me

홈 › Papers

CDRNN: Discovering Complex Dynamics in Human Language Processing

2021-08-01 · ACL 2021 5 · Cory Shain

The human mind is a dynamical system, yet many analysis techniques used to study it are limited in their ability to capture the complex dynamics that may characterize mental processes. This study proposes the continuous-time deconvolutional regressive neural network (CDRNN), a deep neural extension of continuous-time deconvolutional regression (Shain {\&} Schuler, 2021) that jointly captures time-varying, non-linear, and delayed influences of predictors (e.g. word surprisal) on the response (e.g. reading time). Despite this flexibility, CDRNN is interpretable and able to illuminate patterns in human cognition that are otherwise difficult to study. Behavioral and fMRI experiments reveal detailed and plausible estimates of human language processing dynamics that generalize better than CDR and other baselines, supporting a potential role for CDRNN in studying human language processing.

📄 PDF Abstract BibTeX

Code (1)

coryshain/cdr 공식 구현 tf

Tasks

regression

Similar Papers 제목 키워드 기반

Discovering dynamical laws for speech gestures

2025-04-07 · Sam Kirkham

A fundamental challenge in the cognitive sciences is discovering the dynamics that govern behaviour. Take the example of spoken language, which is characterised by a highly variable and complex set of physical movements …

Model DiscoverySymbolic Regression

Advancing network resilience theories with symbolized reinforcement learning

2025-07-04 · Yu Zheng, Jingtao Ding, Depeng Jin, Jianxi Gao 외 arxiv

Many complex networks display remarkable resilience under external perturbations, internal failures and environmental changes, yet they can swiftly deteriorate into dysfunction upon the removal of a few keystone nodes. D…

Reinforcement Learning

MOCHA: Discovering Multi-Order Dynamic Causality in Temporal Point Processes

2025-08-26 · Yunyang Cao, Juekai Lin, Wenhao Li, Bo Jin arxiv

Discovering complex causal dependencies in temporal point processes (TPPs) is critical for modeling real-world event sequences. Existing methods typically rely on static or first-order causal structures, overlooking the …

Point Processes

A Data-Driven Framework for Discovering Fractional Differential Equations in Complex Systems

2024-12-05 · Xiangnan Yu, Hao Xu, Zhiping Mao, Hongguang Sun 외

In complex physical systems, conventional differential equations often fall short in capturing non-local and memory effects, as they are limited to local dynamics and integer-order interactions. This study introduces a s…

Denoisingglobal-optimization

GenAI-Net: A Generative AI Framework for Automated Biomolecular Network Design

2026-01-24 · Maurice Filo, Nicolò Rossi, Zhou Fang, Mustafa Khammash arxiv

Biomolecular networks underpin emerging technologies in synthetic biology-from robust biomanufacturing and metabolic engineering to smart therapeutics and cell-based diagnostics-and also provide a mechanistic language fo…