"recurrent neural networks" Papers
30 papers found
Conference
BRAID: Input-driven Nonlinear Dynamical Modeling of Neural-Behavioral Data
Parsa Vahidi, Omid G. Sani, Maryam Shanechi
Compositional Reasoning with Transformers, RNNs, and Chain of Thought
Gilad Yehudai, Noah Amsel, Joan Bruna
Concept-Guided Interpretability via Neural Chunking
Shuchen Wu, Stephan Alaniz, Shyamgopal Karthik et al.
Efficient Allocation of Working Memory Resource for Utility Maximization in Humans and Recurrent Neural Networks
Qingqing Yang, Hsin-Hung Li
Expressivity of Neural Networks with Random Weights and Learned Biases
Ezekiel Williams, Alexandre Payeur, Avery Ryoo et al.
Flow Equivariant Recurrent Neural Networks
Andy Keller
Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access
Xiang Hu, Jiaqi Leng, Jun Zhao et al.
High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable model
Valentin Schmutz, Ali Haydaroğlu, Shuqi Wang et al.
Language Models Need Inductive Biases to Count Inductively
Yingshan Chang, Yonatan Bisk
Locally Connected Echo State Networks for Time Series Forecasting
Filip Matzner, František Mráz
Mechanistic Interpretability of RNNs emulating Hidden Markov Models
Elia Torre, Michele Viscione, Lucas Pompe et al.
Metric Automata Theory: A Unifying Theory of RNNs
Adam Dankowiakowski, Alessandro Ronca
Nonparametric Quantile Regression with ReLU-Activated Recurrent Neural Networks
Hang Yu, Lyumin Wu, Wenxin Zhou et al.
On Conformal Isometry of Grid Cells: Learning Distance-Preserving Position Embedding
Dehong Xu, Ruiqi Gao, Wenhao Zhang et al.
RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling
Xiuying Wei, Anunay Yadav, Razvan Pascanu et al.
Real-Time Recurrent Reinforcement Learning
Julian Lemmel, Radu Grosu
Revisiting Bi-Linear State Transitions in Recurrent Neural Networks
Reza Ebrahimi, Roland Memisevic
Revisiting Glorot Initialization for Long-Range Linear Recurrences
Noga Bar, Mariia Seleznova, Yotam Alexander et al.
RNNs are not Transformers (Yet): The Key Bottleneck on In-Context Retrieval
Kaiyue Wen, Xingyu Dang, Kaifeng Lyu
ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models
Guoyizhe Wei, Rama Chellappa
Volume Transmission Implements Context Factorization to Target Online Credit Assignment and Enable Compositional Generalization
Matthew Bull, Po-Chen Kuo, Andrew Smith et al.
Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
Sina Khajehabdollahi, Roxana Zeraati, Emmanouil Giannakakis et al.
Exploiting Symmetric Temporally Sparse BPTT for Efficient RNN Training
Xi Chen, Chang Gao, Zuowen Wang et al.
Hidden Traveling Waves bind Working Memory Variables in Recurrent Neural Networks
Arjun Karuvally, Terrence Sejnowski, Hava Siegelmann
Learning Useful Representations of Recurrent Neural Network Weight Matrices
Vincent Herrmann, Francesco Faccio, Jürgen Schmidhuber
PixelRNN: In-pixel Recurrent Neural Networks for End-to-end–optimized Perception with Neural Sensors
Haley So, Laurie Bose, Piotr Dudek et al.
Position: Categorical Deep Learning is an Algebraic Theory of All Architectures
Bruno Gavranović, Paul Lessard, Andrew Dudzik et al.
Rethinking Transformers in Solving POMDPs
Chenhao Lu, Ruizhe Shi, Yuyao Liu et al.
Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks
Khurram Javed, Haseeb Shah, Richard Sutton et al.
The Illusion of State in State-Space Models
William Merrill, Jackson Petty, Ashish Sabharwal