Sensitivity-Guided Framework for Pruned and Quantized Reservoir Computing Accelerators

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jafari, Atousa, Taheri, Mahdi, Mohammadi, Hassan Ghasemzadeh, Herglotz, Christian, Platzner, Marco
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918380571721728
author Jafari, Atousa
Taheri, Mahdi
Mohammadi, Hassan Ghasemzadeh
Herglotz, Christian
Platzner, Marco
author_facet Jafari, Atousa
Taheri, Mahdi
Mohammadi, Hassan Ghasemzadeh
Herglotz, Christian
Platzner, Marco
contents This paper presents a compression framework for Reservoir Computing that enables systematic design-space exploration of trade-offs among quantization levels, pruning rates, model accuracy, and hardware efficiency. The proposed approach leverages a sensitivity-based pruning mechanism to identify and remove less critical quantized weights with minimal impact on model accuracy, thereby reducing computational overhead while preserving accuracy. We perform an extensive trade-off analysis to validate the effectiveness of the proposed framework and the impact of pruning and quantization on model performance and hardware parameters. For this evaluation, we employ three time-series datasets, including both classification and regression tasks. Experimental results across selected benchmarks demonstrate that our proposed approach maintains high accuracy while substantially improving computational and resource efficiency in FPGA-based implementations, with variations observed across different configurations and time series applications. For instance, for the MELBOEN dataset, an accelerator quantized to 4-bit at a 15\% pruning rate reduces resource utilization by 1.2\% and the Power Delay Product (PDP) by 50.8\% compared to an unpruned model, without any noticeable degradation in accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08737
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Sensitivity-Guided Framework for Pruned and Quantized Reservoir Computing Accelerators
Jafari, Atousa
Taheri, Mahdi
Mohammadi, Hassan Ghasemzadeh
Herglotz, Christian
Platzner, Marco
Hardware Architecture
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Machine Learning
This paper presents a compression framework for Reservoir Computing that enables systematic design-space exploration of trade-offs among quantization levels, pruning rates, model accuracy, and hardware efficiency. The proposed approach leverages a sensitivity-based pruning mechanism to identify and remove less critical quantized weights with minimal impact on model accuracy, thereby reducing computational overhead while preserving accuracy. We perform an extensive trade-off analysis to validate the effectiveness of the proposed framework and the impact of pruning and quantization on model performance and hardware parameters. For this evaluation, we employ three time-series datasets, including both classification and regression tasks. Experimental results across selected benchmarks demonstrate that our proposed approach maintains high accuracy while substantially improving computational and resource efficiency in FPGA-based implementations, with variations observed across different configurations and time series applications. For instance, for the MELBOEN dataset, an accelerator quantized to 4-bit at a 15\% pruning rate reduces resource utilization by 1.2\% and the Power Delay Product (PDP) by 50.8\% compared to an unpruned model, without any noticeable degradation in accuracy.
title Sensitivity-Guided Framework for Pruned and Quantized Reservoir Computing Accelerators
topic Hardware Architecture
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Machine Learning
url https://arxiv.org/abs/2603.08737