paper-with-me

Papers

Low-Dimensional Manifolds Support Multiplexed Integrations in Recurrent Neural Networks

2020-11-20 · Arnaud Fanthomme, Rémi Monasson

We study the learning dynamics and the representations emerging in Recurrent Neural Networks trained to integrate one or multiple temporal signals. Combining analytical and numerical investigations, we characterize the conditions under which a RNN with n neurons learns to integrate D(n) scalar signals of arbitrary duration. We show, both for linear and ReLU neurons, that its internal state lives close to a D-dimensional manifold, whose shape is related to the activation function. Each neuron therefore carries, to various degrees, information about the value of all integrals. We discuss the deep analogy between our results and the concept of mixed selectivity forged by computational neuroscientists to interpret cortical recordings.

📄 PDF Abstract BibTeX arXiv:2011.10435

Code (1)

AFanthomme/ManifoldsSupportRNI 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Embedding of Low-Dimensional Sensory Dynamics in Recurrent Networks: Implications for the Geometry of Neural Representation

2026-01-26 · Vikas N. O'Reilly-Shah, Alessandro Maria Selvitella arxiv

Neural population activity in sensory cortex is organized on low-dimensional manifolds, but why such manifolds arise and what determines their geometry remain unclear. We model cortical populations as recurrent circuits …

Constructive Disintegration and Conditional Modes

2025-08-01 · Nathaël Da Costa, Marvin Pförtner, Jon Cockayne arxiv

Conditioning, the central operation in Bayesian statistics, is formalised by the notion of disintegration of measures. However, due to the implicit nature of their definition, constructing disintegrations is often diffic…

Bayesian Inference

On Dominant Manifolds in Reservoir Computing Networks

2026-04-07 · Noa Kaplan, Alberto Padoan, Anastasia Bizyaeva arxiv

Understanding how training shapes the geometry of recurrent network dynamics is a central problem in time-series modeling. We study the emergence of low-dimensional dominant manifolds in the training of Reservoir Computi…

Conformal Embedding Flows: Tractable Density Estimation on Learned Manifolds

2021-06-02 · ICML Workshop INNF 2021 7 · Brendan Leigh Ross, Jesse C Cresswell

Normalizing flows are generative models that provide tractable density estimation by transforming a simple distribution into a complex one. However, flows cannot directly model data supported on an unknown low-dimensiona…

Density Estimation

PepSIRF: a flexible and comprehensive tool for the analysis of data from highly-multiplexed DNA-barcoded peptide assays

2020-07-09 · Zane W. Fink, Vidal Martinez, John Altin, Jason T. Ladner

By coupling peptides with DNA tags (i.e., 'barcodes'), it is now possible to harness high-throughput sequencing (HTS) technologies to enable highly multiplexed peptide-based assays, which have a variety of potential appl…