paper-with-me

홈 › Papers

Sufficient conditions for offline reactivation in recurrent neural networks

2025-05-22 · Internation Conference on Learning Representations 2024 1 · Nanda H. Krishna, Colin Bredenberg, Daniel Levenstein, Blake A. Richards, Guillaume Lajoie

During periods of quiescence, such as sleep, neural activity in many brain circuits resembles that observed during periods of task engagement. However, the precise conditions under which task-optimized networks can autonomously reactivate the same network states responsible for online behavior is poorly understood. In this study, we develop a mathematical framework that outlines sufficient conditions for the emergence of neural reactivation in circuits that encode features of smoothly varying stimuli. We demonstrate mathematically that noisy recurrent networks optimized to track environmental state variables using change-based sensory information naturally develop denoising dynamics, which, in the absence of input, cause the network to revisit state configurations observed during periods of online activity. We validate our findings using numerical experiments on two canonical neuroscience tasks: spatial position estimation based on self-motion cues, and head direction estimation based on angular velocity cues. Overall, our work provides theoretical support for modeling offline reactivation as an emergent consequence of task optimization in noisy neural circuits.

📄 PDF Abstract BibTeX arXiv:2505.17003

Code (1)

nandahkrishna/RNNReactivation 공식 구현 pytorch

Tasks

Denoising

Similar Papers 제목 키워드 기반

The Nonequilibrium Mechanism of Noise Enhancer synergizing with Activator in HIV Latency Reactivation

2020-01-15 · Xiaolu Guo, Tao Tang, Minxuan Duan, Lei Zhang 외

Noise-modulating chemicals can synergize with transcriptional activators in reactivating latent HIV to eliminate latent HIV reservoirs. To understand the underlying biomolecular mechanism, we investigate a previous two-g…

Translation

Bayesian Sparsification of Gated Recurrent Neural Networks

2018-12-12 · NIPS Workshop CDNNRIA 2018 · Ekaterina Lobacheva, Nadezhda Chirkova, Dmitry Vetrov

Bayesian methods have been successfully applied to sparsify weights of neural networks and to remove structure units from the networks, e. g. neurons. We apply and further develop this approach for gated recurrent archit…

Structured Sparsification of Gated Recurrent Neural Networks

2019-11-13 · Ekaterina Lobacheva, Nadezhda Chirkova, Alexander Markovich, Dmitry Vetrov

Recently, a lot of techniques were developed to sparsify the weights of neural networks and to remove networks' structure units, e.g. neurons. We adjust the existing sparsification approaches to the gated recurrent archi…

Language ModelingLanguage Modellingtext-classificationText Classification

Densely Connected $G$-invariant Deep Neural Networks with Signed Permutation Representations

2023-03-08 · Devanshu Agrawal, James Ostrowski

We introduce and investigate, for finite groups $G$, $G$-invariant deep neural network ($G$-DNN) architectures with ReLU activation that are densely connected-- i.e., include all possible skip connections. In contrast to…

3D Object Classification

A recurrent vision transformer shows signatures of primate visual attention

2025-02-16 · Jonathan Morgan, Badr Albanna, James P. Herman

Attention is fundamental to both biological and artificial intelligence, yet research on animal attention and AI self attention remains largely disconnected. We propose a Recurrent Vision Transformer (Recurrent ViT) that…

Change Detection