A training algorithm for networks of high-variability reservoirs
| Autor: | Joni Dambre, Matthias Freiberger, Peter Bienstman |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
Technology and Engineering Computer science media_common.quotation_subject MathematicsofComputing_NUMERICALANALYSIS lcsh:Medicine Article 03 medical and health sciences 0302 clinical medicine SYSTEMS recurrent neural networks Simplicity lcsh:Science media_common Multidisciplinary Artificial neural network Photonic devices lcsh:R Reservoir computing Backpropagation Electrical and electronic engineering Power (physics) Task (computing) target signal derivation 030104 developmental biology Recurrent neural network deep reservoir computing multi-reservoir architectures lcsh:Q State (computer science) NEURAL-NETWORKS training algorithms Algorithm 030217 neurology & neurosurgery |
| Zdroj: | SCIENTIFIC REPORTS Scientific Reports Scientific Reports, Vol 10, Iss 1, Pp 1-11 (2020) |
| ISSN: | 2045-2322 |
| Popis: | Physical reservoir computing approaches have gained increased attention in recent years due to their potential for low-energy high-performance computing. Despite recent successes, there are bounds to what one can achieve simply by making physical reservoirs larger. Therefore, we argue that a switch from single-reservoir computing to multi-reservoir and even deep physical reservoir computing is desirable. Given that error backpropagation cannot be used directly to train a large class of multi-reservoir systems, we propose an alternative framework that combines the power of backpropagation with the speed and simplicity of classic training algorithms. In this work we report our findings on a conducted experiment to evaluate the general feasibility of our approach. We train a network of 3 Echo State Networks to perform the well-known NARMA-10 task, where we use intermediate targets derived through backpropagation. Our results indicate that our proposed method is well-suited to train multi-reservoir systems in an efficient way. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|