Benchmarking Learning Efficiency in Deep Reservoir Computing

TL;DR

This paper introduces a benchmark to evaluate the data efficiency and learning speed of various machine learning models, revealing that reservoir computing systems often learn faster than traditional supervised models while maintaining similar accuracy.

Contribution

It presents a new benchmark and data efficiency metric for comparing learning speeds across models, highlighting reservoir computing's advantages.

Findings

Reservoir computing learns faster than RNNs, LSTMs, and Transformers.

Reservoir systems achieve comparable accuracy with less training data.

The benchmark and code are publicly available for reproducibility.

Abstract

It is common to evaluate the performance of a machine learning model by measuring its predictive power on a test dataset. This approach favors complicated models that can smoothly fit complex functions and generalize well from training data points. Although essential components of intelligence, speed and data efficiency of this learning process are rarely reported or compared between different candidate models. In this paper, we introduce a benchmark of increasingly difficult tasks together with a data efficiency metric to measure how quickly machine learning models learn from training data. We compare the learning speed of some established sequential supervised models, such as RNNs, LSTMs, or Transformers, with relatively less known alternative models based on reservoir computing. The proposed tasks require a wide range of computational primitives, such as memory or the ability to compute Boolean functions, to be effectively solved. Surprisingly, we observe that reservoir computing systems that rely on dynamically evolving feature maps learn faster than fully supervised methods trained with stochastic gradient optimization while achieving comparable accuracy scores. The code, benchmark, trained models, and results to reproduce our experiments are available at https://github.com/hugcis/benchmark_learning_efficiency/ .