paper-with-me

Papers

RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks

2021-06-16 · Leo Kozachkov, Michaela Ennis, Jean-Jacques Slotine

Recurrent neural networks (RNNs) are widely used throughout neuroscience as models of local neural activity. Many properties of single RNNs are well characterized theoretically, but experimental neuroscience has moved in the direction of studying multiple interacting areas, and RNN theory needs to be likewise extended. We take a constructive approach towards this problem, leveraging tools from nonlinear control theory and machine learning to characterize when combinations of stable RNNs will themselves be stable. Importantly, we derive conditions which allow for massive feedback connections between interacting RNNs. We parameterize these conditions for easy optimization using gradient-based techniques, and show that stability-constrained "networks of networks" can perform well on challenging sequential-processing benchmark tasks. Altogether, our results provide a principled approach towards understanding distributed, modular function in the brain.

📄 PDF Abstract BibTeX arXiv:2106.08928

Code (1)

ennisthemennis/sparse-combo-net 공식 구현

Tasks

Sequential Image Classification

Similar Papers 제목 키워드 기반

Contraction Properties of the Global Workspace Primitive

2023-10-02 · Michaela Ennis, Leo Kozachkov, Jean-Jacques Slotine

To push forward the important emerging research field surrounding multi-area recurrent neural networks (RNNs), we expand theoretically and empirically on the provably stable RNNs of RNNs introduced by Kozachkov et al. in…

Overall - Test

Detecting Invariant Manifolds in ReLU-Based RNNs

2025-10-04 · Lukas Eisenmann, Alena Brändle, Zahra Monfared, Daniel Durstewitz arxiv

Recurrent Neural Networks (RNNs) have found widespread applications in machine learning for time series prediction and dynamical systems reconstruction, and experienced a recent renaissance with improved training algorit…

Time Series Prediction

Can RNNs learn Recursive Nested Subject-Verb Agreements?

2021-01-06 · Yair Lakretz, Théo Desbordes, Jean-Rémi King, Benoît Crabbé 외

One of the fundamental principles of contemporary linguistics states that language processing requires the ability to extract recursively nested tree structures. However, it remains unclear whether and how this code coul…

Sentence

Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks

2025-06-02 · Taisuke Kobayashi, Shingo Murata

This paper proposes a novel stable learning theory for recurrent neural networks (RNNs), so-called variational adaptive noise and dropout (VAND). As stabilizing factors for RNNs, noise and dropout on the internal state o…

Imitation LearningLearning TheoryVariational Inference

Grounded Compositional Semantics for Finding and Describing Images with Sentences

2014-01-01 · TACL 2014 1 · Richard Socher, Andrej Karpathy, Quoc V. Le, Christopher D. Manning 외

Previous work on Recursive Neural Networks (RNNs) shows that these models can produce compositional feature vectors for accurately representing and classifying sentences or images. However, the sentence vectors of previo…

Sentence