# FPGA Implementation of Next-Generation Reservoir Computing for predicting dynamical systems

- Institution: CERN
- Department: FPGA Developers' Forum (FDF)
- Speaker: João Folhadela
- Year: 2025
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3021084)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

Reservoir Computing (RC) is a new paradigm in Machine Learning, alternative to Neural Networks on predicting dynamical systems, offering advantages in efficiency and computational simplicity. These characteristics make RC particularly well-suited for implementation on resource-constrained hardware such as FPGAs, enabling low-power, real-time edge computing. Next-Generation Reservoir Computing (NG-RC) further enhances this approach by significantly reducing the number of required parameters compared to conventional RC, making FPGA implementations even more efficient. In this work, we present an FPGA-based implementation of NG-RC for predicting the Lorenz attractor, demonstrating its effectiveness in modeling chaotic systems with minimal computational overhead..

0:00:00 Slide 1

0:01:12 Slide 2

0:04:56 Slide 3

0:06:54 Slide 4

0:10:16 Slide 5

0:11:18 Slide 6

0:12:45 Slide 7

## Lectures

1. [FPGA Implementation of Next-Generation Reservoir Computing for predicting dynamical systems](https://invisiblenetwork.ai/learn/cern/3021084/8e7c3f962b52), 16 min (CERN's player)