Benchmarking Learning Efficiency in Deep Reservoir Computing
This work addresses the need for standardized efficiency benchmarks in machine learning, which is incremental as it builds on existing model comparisons but focuses on an underreported aspect.
The authors tackled the problem of evaluating learning speed and data efficiency in machine learning models by introducing a benchmark with tasks requiring various computational primitives. They found that reservoir computing systems learn faster than established supervised methods like RNNs and LSTMs while achieving comparable accuracy.
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/ .