paper-with-me

홈 › Papers

Realization Theory Of Recurrent Neural ODEs Using Polynomial System Embeddings

2022-05-24 · Martin Gonzalez, Thibault Defourneau, Hatem Hajri, Mihaly Petreczky

In this paper we show that neural ODE analogs of recurrent (ODE-RNN) and Long Short-Term Memory (ODE-LSTM) networks can be algorithmically embeddeded into the class of polynomial systems. This embedding preserves input-output behavior and can suitably be extended to other neural DE architectures. We then use realization theory of polynomial systems to provide necessary conditions for an input-output map to be realizable by an ODE-LSTM and sufficient conditions for minimality of such systems. These results represent the first steps towards realization theory of recurrent neural ODE architectures, which is is expected be useful for model reduction and learning algorithm analysis of recurrent neural ODEs.

📄 PDF Abstract BibTeX arXiv:2205.11989

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Dimension reduction in recurrent networks by canonicalization

2020-07-23 · Lyudmila Grigoryeva, Juan-Pablo Ortega

Many recurrent neural network machine learning paradigms can be formulated using state-space representations. The classical notion of canonical state-space realization is adapted in this paper to accommodate semi-infinit…

Dimensionality Reduction

SHiPPO: Recurrent Memory with Transported Polynomial Projections

2026-07-03 · Tomoya Mizuguchi, Bum Jun Kim arxiv

HiPPO gives recurrent states memory semantics as coefficients of online polynomial projections, but in fixed channel coordinates. Modern selective SSMs, by contrast, rely on token-dependent control and channel interactio…

Interpretable Design of Reservoir Computing Networks using Realization Theory

2021-12-13 · Wei Miao, Vignesh Narayanan, Jr-Shin Li

The reservoir computing networks (RCNs) have been successfully employed as a tool in learning and complex decision-making tasks. Despite their efficiency and low training cost, practical applications of RCNs rely heavily…

Decision Making

Primitive Recursion without Composition: Dynamical Characterizations, from Neural Networks to Polynomial ODEs

2026-04-27 · Olivier Bournez arxiv

What do recurrent neural networks, polynomial ODEs, and discrete polynomial maps each bring to computation, and what do they lack? All three operate over the continuum--real-valued states evolved by real-valued dynamics-…

Approximating meta-heuristics with homotopic recurrent neural networks

2017-09-07 · Alessandro Bay, Biswa Sengupta

Much combinatorial optimisation problems constitute a non-polynomial (NP) hard optimisation problem, i.e., they can not be solved in polynomial time. One such problem is finding the shortest route between two nodes on a …

Reinforcement LearningReinforcement Learning (RL)