# Sensitivity-Guided Framework for Pruned and Quantized Reservoir Computing Accelerators

arXiv: https://arxiv.org/abs/2603.08737 · HTML: https://mlsanity.com/paper/2603.08737/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## Builds on (most cited first, 6 of 6)

- [Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search](https://mlsanity.com/paper/1903.12269/) (2019)
- [LogicNets: Co-Designed Neural Networks and Circuits for Extreme-Throughput Applications](https://mlsanity.com/paper/2004.03021/) (2020)
- [Reservoir computing approaches for representation and classification of multivariate time series](https://mlsanity.com/paper/1803.07870/) (2018)
- [Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning](https://mlsanity.com/paper/2004.11627/) (2020)
- [Streamlined Deployment for Quantized Neural Networks](https://mlsanity.com/paper/1709.04060/) (2017)
- [HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs](https://mlsanity.com/paper/2602.16336/) (2026)

## Built on by (most cited first, 2 of 2)

- [Mix-and-Match Pruning: Globally Guided Layer-Wise Sparsification of DNNs](https://mlsanity.com/paper/2603.20280/) (2026)
- [Effective Training Principles of Physical Reservoirs](https://mlsanity.com/paper/2606.10130/) (2026)

## Abstract (arXiv)

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.