Presentation Type

Poster

Start Date

5-8-2024 11:00 AM

End Date

5-8-2024 1:00 PM

Subjects

Machine learning, Neural networks (Computer science)

Advisor

Christof Teuscher

Student Level

Undergraduate

Abstract

In this poster, we present a systematic evaluation and comparison of five Reservoir computing (RC) software simulation frameworks, namely reservoirpy, RcTorch, pyRCN, pytorch-esn, and ReservoirComputing.jl. RC is a specific machine learning approach that leverages fixed, nonlinear systems to map signals into higher dimensions. Its unique strength lies in training only the readout layer, which reduces the training complexity. RC excels in temporal signal processing and is also well suited for various physical implementations. The increasing interest in RC has led to the proliferation of various RC simulation frameworks. Our RC simulation framework evaluation focuses on a feature comparison, documentation quality, and performance across three benchmark tasks. Our results show that pytorch-esn outperforms the other frameworks by order of magnitude in total network training time. All frameworks show similar scaling behavior with increasing reservoir size. Reservoirpy stands out for its comprehensive set of features, offering unparalleled support for designing highly customizable simulations. Our evaluation will help researchers, practitioners, and students to select the right RC simulation framework for their tasks at hand.

Creative Commons License or Rights Statement

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Persistent Identifier

https://archives.pdx.edu/ds/psu/41862

Share

COinS
 
May 8th, 11:00 AM May 8th, 1:00 PM

Systematic Comparison of Reservoir Computing Frameworks

In this poster, we present a systematic evaluation and comparison of five Reservoir computing (RC) software simulation frameworks, namely reservoirpy, RcTorch, pyRCN, pytorch-esn, and ReservoirComputing.jl. RC is a specific machine learning approach that leverages fixed, nonlinear systems to map signals into higher dimensions. Its unique strength lies in training only the readout layer, which reduces the training complexity. RC excels in temporal signal processing and is also well suited for various physical implementations. The increasing interest in RC has led to the proliferation of various RC simulation frameworks. Our RC simulation framework evaluation focuses on a feature comparison, documentation quality, and performance across three benchmark tasks. Our results show that pytorch-esn outperforms the other frameworks by order of magnitude in total network training time. All frameworks show similar scaling behavior with increasing reservoir size. Reservoirpy stands out for its comprehensive set of features, offering unparalleled support for designing highly customizable simulations. Our evaluation will help researchers, practitioners, and students to select the right RC simulation framework for their tasks at hand.