---
_id: '62184'
abstract:
- lang: eng
text: While reservoir computing (RC) networks offer advantages over traditional
recurrent neural net- works in terms of training time and operational cost for
time-series applications, deploying them on edge devices still presents significant
challenges due to re- source constraints. Network compression, i.e., pruning and
quantization, are thus of utmost importance. We propose a Compressed Reservoir
Computing (CRC) framework that integrates advanced pruning and quantization techniques
to optimize throughput, latency, energy efficiency, and resource utilization for
FPGA- based RC accelerators.We describe the framework with a focus on HSIC LASSO
as a novel pruning method that can capture non-linear dependencies between neurons.
We validate our framework with time series classification and regression tasks,
for which we generate FPGA accelerators. The accelerators achieve a very high
throughput of up to 188 Megasamples/s with a latency of 5.32 ns, while reducing
resource utilization by 12× and lowering the energy by 10× compared to a baseline
hardware implementation, without compromising accuracy.
article_number: '4'
author:
- first_name: Atousa
full_name: Jafari, Atousa
last_name: Jafari
- first_name: Hassan
full_name: Ghasemzadeh Mohammadi, Hassan
last_name: Ghasemzadeh Mohammadi
- first_name: Marco
full_name: Platzner, Marco
last_name: Platzner
citation:
ama: 'Jafari A, Ghasemzadeh Mohammadi H, Platzner M. CRC: Compressed Reservoir Computing
on FPGA via Joint HSIC LASSO-based Pruning and Quantization. WiPiEC Journal
- Works in Progress in Embedded Computing Journal. 2025;11(1). doi:10.64552/wipiec.v11i1.99'
apa: 'Jafari, A., Ghasemzadeh Mohammadi, H., & Platzner, M. (2025). CRC: Compressed
Reservoir Computing on FPGA via Joint HSIC LASSO-based Pruning and Quantization.
WiPiEC Journal - Works in Progress in Embedded Computing Journal, 11(1),
Article 4. https://doi.org/10.64552/wipiec.v11i1.99'
bibtex: '@article{Jafari_Ghasemzadeh Mohammadi_Platzner_2025, title={CRC: Compressed
Reservoir Computing on FPGA via Joint HSIC LASSO-based Pruning and Quantization},
volume={11}, DOI={10.64552/wipiec.v11i1.99},
number={14}, journal={WiPiEC Journal - Works in Progress in Embedded Computing
Journal}, publisher={MECOnet}, author={Jafari, Atousa and Ghasemzadeh Mohammadi,
Hassan and Platzner, Marco}, year={2025} }'
chicago: 'Jafari, Atousa, Hassan Ghasemzadeh Mohammadi, and Marco Platzner. “CRC:
Compressed Reservoir Computing on FPGA via Joint HSIC LASSO-Based Pruning and
Quantization.” WiPiEC Journal - Works in Progress in Embedded Computing Journal
11, no. 1 (2025). https://doi.org/10.64552/wipiec.v11i1.99.'
ieee: 'A. Jafari, H. Ghasemzadeh Mohammadi, and M. Platzner, “CRC: Compressed Reservoir
Computing on FPGA via Joint HSIC LASSO-based Pruning and Quantization,” WiPiEC
Journal - Works in Progress in Embedded Computing Journal, vol. 11, no. 1,
Art. no. 4, 2025, doi: 10.64552/wipiec.v11i1.99.'
mla: 'Jafari, Atousa, et al. “CRC: Compressed Reservoir Computing on FPGA via Joint
HSIC LASSO-Based Pruning and Quantization.” WiPiEC Journal - Works in Progress
in Embedded Computing Journal, vol. 11, no. 1, 4, MECOnet, 2025, doi:10.64552/wipiec.v11i1.99.'
short: A. Jafari, H. Ghasemzadeh Mohammadi, M. Platzner, WiPiEC Journal - Works
in Progress in Embedded Computing Journal 11 (2025).
date_created: 2025-11-14T05:48:05Z
date_updated: 2025-11-14T09:35:16Z
doi: 10.64552/wipiec.v11i1.99
intvolume: ' 11'
issue: '1'
publication: WiPiEC Journal - Works in Progress in Embedded Computing Journal
publication_identifier:
issn:
- 2980-7298
- 2337-0343
publication_status: published
publisher: MECOnet
status: public
title: 'CRC: Compressed Reservoir Computing on FPGA via Joint HSIC LASSO-based Pruning
and Quantization'
type: journal_article
user_id: '99966'
volume: 11
year: '2025'
...