English
Related papers

Related papers: Credit Assignment for Trained Neural Networks Base…

200 papers

In this paper, a new method for assigning credit to search operators is presented. Starting with the principle of optimizing search bias, search operators are selected based on an ability to create solutions that are historically linked to…

Neural and Evolutionary Computing · Computer Science 2009-07-06 James M. Whitacre , Tuan Q. Pham , Ruhul A. Sarker

Distributed learning is the problem of inferring a function in the case where training data is distributed among multiple geographically separated sources. Particularly, the focus is on designing learning strategies with low computational…

Machine Learning · Statistics 2016-07-22 Simone Scardapane

The theory of Koopman operators allows to deploy non-parametric machine learning algorithms to predict and analyze complex dynamical systems. Estimators such as principal component regression (PCR) or reduced rank regression (RRR) in kernel…

In this work, we develop a method to identify continuous-time nonlinear networked dynamics via the Koopman operator framework. The proposed technique consists of two steps: the first step identifies the neighbors of each node, and the…

Systems and Control · Electrical Eng. & Systems 2024-12-25 Ramachandran Anantharaman , Alexandre Mauroy

In this paper, we propose a novel algorithm for learning the Koopman operator of a dynamical system from a \textit{small} amount of training data. In many applications of data-driven modeling, e.g. biological network modeling,…

Dynamical Systems · Mathematics 2021-03-09 Subhrajit Sinha , Umesh Vaidya , Enoch Yeung

Koopman operator theory provides a powerful framework for representing nonlinear dynamics through a linear operator acting on lifted observables, enabling the use of linear control techniques for nonlinear systems. However, Koopman models…

Robotics · Computer Science 2026-05-12 Chandan Kumar Sah , Rajpal Singh , Jishnu Keshavan

Over the last few years, several works have proposed deep learning architectures to learn dynamical systems from observation data with no or little knowledge of the underlying physics. A line of work relies on learning representations where…

Machine Learning · Computer Science 2023-03-14 Anthony Frion , Lucas Drumetz , Mauro Dalla Mura , Guillaume Tochon , Abdeldjalil Aissa El Bey

The Koopman operator and its data-driven approximations, such as extended dynamic mode decomposition (EDMD), are widely used for analysing, modelling, and controlling nonlinear dynamical systems. However, when the true Koopman…

Dynamical Systems · Mathematics 2026-02-05 Roland Schurig , Pieter van Goor , Karl Worthmann , Rolf Findeisen

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Aziz Bacha , Thomas George

Neural network models and deep models are one of the leading and state of the art models in machine learning. Most successful deep neural models are the ones with many layers which highly increases their number of parameters. Training such…

Machine Learning · Computer Science 2018-07-17 Soufiane Belharbi

This paper explores a simple question: can we model the internal transformations of a neural network using dynamical systems theory? We introduce Koopman autoencoders to capture how neural representations evolve through network layers,…

Machine Learning · Computer Science 2025-05-20 Nishant Suresh Aswani , Saif Eddin Jabari

Spectral decomposition of dynamical systems is a popular methodology to investigate the fundamental qualitative and quantitative properties of these systems and their solutions. In this chapter, we consider a class of nonlinear cooperative…

Systems and Control · Computer Science 2019-04-23 Hossein K. Mousavi , Christoforos Somarakis , Qiyu Sun , Nader Motee

The field of dynamical systems is being transformed by the mathematical tools and algorithms emerging from modern computing and data science. First-principles derivations and asymptotic reductions are giving way to data-driven approaches…

Dynamical Systems · Mathematics 2021-11-02 Steven L. Brunton , Marko Budišić , Eurika Kaiser , J. Nathan Kutz

Continuous-depth neural networks, such as Neural ODEs, have refashioned the understanding of residual neural networks in terms of non-linear vector-valued optimal control problems. The common solution is to use the adjoint sensitivity…

Machine Learning · Computer Science 2022-02-16 Andrew Corbett , Dmitry Kangin

The Koopman operator is a linear operator that describes the evolution of scalar observables (i.e., measurement functions of the states) in an infinitedimensional Hilbert space. This operator theoretic point of view lifts the dynamics of a…

Optimization and Control · Mathematics 2021-10-19 Gregory Snyder , Zhuoyuan Song

Most modern reinforcement learning algorithms optimize a cumulative single-step cost along a trajectory. The optimized motions are often 'unnatural', representing, for example, behaviors with sudden accelerations that waste energy and lack…

Machine Learning · Computer Science 2024-07-03 Motoya Ohnishi , Isao Ishikawa , Kendall Lowrey , Masahiro Ikeda , Sham Kakade , Yoshinobu Kawahara

Learning depends on changes in synaptic connections deep inside the brain. In multilayer networks, these changes are triggered by error signals fed back from the output, generally through a stepwise inversion of the feedforward processing…

Neurons and Cognition · Quantitative Biology 2021-01-05 William F. Podlaski , Christian K. Machens

Koopman linear representations have become a popular tool for control design of nonlinear systems, yet it remains unclear when such representations are exact. In this paper, we establish sufficient and necessary conditions under which a…

Optimization and Control · Mathematics 2026-02-17 Xu Shang , Masih Haseli , Jorge Cortés , Yang Zheng

Efficient credit assignment is essential for reinforcement learning algorithms in both prediction and control settings. We describe a unified view on temporal-difference algorithms for selective credit assignment. These selective algorithms…

Machine Learning · Computer Science 2022-02-22 Veronica Chelu , Diana Borsa , Doina Precup , Hado van Hasselt

Back-propagation has been the workhorse of recent successes of deep learning but it relies on infinitesimal effects (partial derivatives) in order to perform credit assignment. This could become a serious issue as one considers deeper and…

Machine Learning · Computer Science 2015-11-26 Dong-Hyun Lee , Saizheng Zhang , Asja Fischer , Yoshua Bengio