English
Related papers

Related papers: Learning Beyond Experience: Generalizing to Unseen…

200 papers

A reservoir computer is a special type of neural network, where most of the weights are randomly fixed and only a subset are trained. In this thesis we prove results about reservoir computers trained on deterministic dynamical systems, and…

Dynamical Systems · Mathematics 2021-12-28 Allen G Hart

Artificial Recurrent Neural Networks are a powerful information processing abstraction, and Reservoir Computing provides an efficient strategy to build robust implementations by projecting external inputs into high dimensional dynamical…

Machine Learning · Computer Science 2021-04-21 Claudio Gallicchio , Alessio Micheli , Luca Silvestri

We propose a physics-constrained machine learning method-based on reservoir computing- to time-accurately predict extreme events and long-term velocity statistics in a model of turbulent shear flow. The method leverages the strengths of two…

Fluid Dynamics · Physics 2021-04-14 Nguyen Anh Khoa Doan , Wolfgang Polifke , Luca Magri

We are motivated by the problem of learning policies for robotic systems with rich sensory inputs (e.g., vision) in a manner that allows us to guarantee generalization to environments unseen during training. We provide a framework for…

Robotics · Computer Science 2022-07-25 Abhinav Agarwal , Sushant Veer , Allen Z. Ren , Anirudha Majumdar

The generalization of model-based reinforcement learning (MBRL) methods to environments with unseen transition dynamics is an important yet challenging problem. Existing methods try to extract environment-specified information $Z$ from past…

Machine Learning · Computer Science 2022-06-10 Jixian Guo , Mingming Gong , Dacheng Tao

Domain Generalization aims to develop models that can generalize to novel and unseen data distributions. In this work, we study how model architectures and pre-training objectives impact feature richness and propose a method to effectively…

Machine Learning · Computer Science 2025-04-30 Xavier Thomas , Deepti Ghadiyaram

The Reservoir Computing (RC) paradigm posits that sufficiently complex physical systems can be used to massively simplify pattern recognition tasks and nonlinear signal prediction. This work demonstrates how random topological magnetic…

Mesoscale and Nanoscale Physics · Physics 2020-11-18 Daniele Pinna , George Bourianoff , Karin Everschor-Sitte

In recent years, Neural Turing Machines have gathered attention by joining the flexibility of neural networks with the computational capabilities of Turing machines. However, Neural Turing Machines are notoriously hard to train, which…

Machine Learning · Computer Science 2020-03-11 Benjamin Paassen , Alexander Schulz

Memristive systems and devices are potentially available for implementing reservoir computing (RC) systems applied to pattern recognition. However, the computational ability of memristive RC systems depends on intertwined factors such as…

Emerging Technologies · Computer Science 2022-06-22 Gouhei Tanaka , Ryosho Nakane

This work considers the problem of transfer learning in the context of reinforcement learning. Specifically, we consider training a policy in a reduced order system and deploying it in the full state system. The motivation for this training…

Machine Learning · Computer Science 2024-10-10 Shima Rabiei , Sandipan Mishra , Santiago Paternain

Since their inception, learning techniques under the Reservoir Computing paradigm have shown a great modeling capability for recurrent systems without the computing overheads required for other approaches. Among them, different flavors of…

Machine Learning · Computer Science 2021-02-18 Alejandro Barredo Arrieta , Sergio Gil-Lopez , Ibai Laña , Miren Nekane Bilbao , Javier Del Ser

The paper presents a novel, principled approach to train recurrent neural networks from the Reservoir Computing family that are robust to missing part of the input features at prediction time. By building on the ensembling properties of…

Machine Learning · Computer Science 2017-05-09 Davide Bacciu , Francesco Crecchi , Davide Morelli

Multifunctionality is ubiquitous in biological neurons. Several studies have translated the concept to artificial neural networks as well. Recently, multifunctionality in reservoir computing (RC) has gained the widespread attention of…

Chaotic Dynamics · Physics 2025-04-18 Swarnendu Mandal , Kazuyuki Aihara

In nonlinear dynamical systems, tipping refers to a critical transition from one steady state to another, typically catastrophic, steady state, often resulting from a saddle-node bifurcation. Recently, the machine-learning framework of…

Chaotic Dynamics · Physics 2026-04-09 Smita Deb , Zheng-Meng Zhai , Mulugeta Haile , Ying-Cheng Lai

Recently, reinforcement learning models have achieved great success, completing complex tasks such as mastering Go and other games with higher scores than human players. Many of these models collect considerable data on the tasks and…

Machine Learning · Computer Science 2019-07-19 Hanten Chang , Katsuya Futagami

Reservoir computing (RC) has attracted attention as an efficient recurrent neural network architecture due to its simplified training, requiring only its last perceptron readout layer to be trained. When implemented with memristors, RC…

Neural and Evolutionary Computing · Computer Science 2025-08-01 Rishona Daniels , Duna Wattad , Ronny Ronen , David Saad , Shahar Kvatinsky

Deep neural networks have gained tremendous success in a broad range of machine learning tasks due to its remarkable capability to learn semantic-rich features from high-dimensional data. However, they often require large-scale labelled…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Hu Wang , Guansong Pang , Chunhua Shen , Congbo Ma

Reservoir computing systems are constructed using a driven dynamical system in which external inputs can alter the evolving states of a system. These paradigms are used in information processing, machine learning, and computation. A…

Neural and Evolutionary Computing · Computer Science 2023-04-26 G Manjunath , Juan-Pablo Ortega

This study evaluates data-driven models from a dynamical system perspective, such as unstable fixed points, periodic orbits, chaotic saddle, Lyapunov exponents, manifold structures, and statistical values. We find that these dynamical…

Dynamical Systems · Mathematics 2021-11-10 Miki U Kobayashi , Kengo Nakai , Yoshitaka Saiki , Natsuki Tsutsumi

Despite impressive performance as evaluated on i.i.d. holdout data, deep neural networks depend heavily on superficial statistics of the training data and are liable to break under distribution shift. For example, subtle changes to the…

Computer Vision and Pattern Recognition · Computer Science 2019-03-18 Haohan Wang , Zexue He , Zachary C. Lipton , Eric P. Xing