Lead Zirconate Titanate Reservoir Computing for Classification of Written and Spoken Digits

TL;DR

This paper demonstrates that Lead Zirconate Titanate (PZT) physical reservoirs can effectively classify handwritten and spoken digits, outperforming simple linear models on intermediate difficulty tasks.

Contribution

The study extends physical reservoir computing to PZT substrates, showing improved digit classification accuracy and highlighting their potential for low-power, integrated computational systems.

Findings

PZT reservoir achieves 89.0% accuracy on MNIST, surpassing logistic regression.

On AudioMNIST, PZT performs comparably to baseline methods with 88.2% accuracy.

Reservoir computing benefits are most evident for tasks of intermediate difficulty.

Abstract

In this paper we extend our earlier work of (Rietman et al. 2022) presenting an application of physical Reservoir Computing (RC) to the classification of handwritten and spoken digits. We utilize an unpoled cube of Lead Zirconate Titanate (PZT) as a computational substrate to process these datasets. Our results demonstrate that the PZT reservoir achieves 89.0% accuracy on MNIST handwritten digits, representing a 2.4 percentage point improvement over logistic regression baselines applied to the same preprocessed data. However, for the AudioMNIST spoken digits dataset, the reservoir system (88.2% accuracy) performs equivalently to baseline methods (88.1% accuracy), suggesting that reservoir computing provides the greatest benefits for classification tasks of intermediate difficulty where linear methods underperform but the problem remains learnable. PZT is a well-known material already used in semiconductor applications, presenting a low-power computational substrate that can be integrated with digital algorithms. Our findings indicate that physical reservoirs excel when the task difficulty exceeds the capability of simple linear classifiers but remains within the computational capacity of the reservoir dynamics.