Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2021
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2108.01512 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911039915819008 |
|---|---|
| author | Love, Jake Mulkers, Jeroen Msiska, Robin Bourianoff, George Leliaert, Jonathan Everschor-Sitte, Karin |
| author_facet | Love, Jake Mulkers, Jeroen Msiska, Robin Bourianoff, George Leliaert, Jonathan Everschor-Sitte, Karin |
| contents | Physical reservoir computing is a computational framework that implements spatiotemporal information processing directly within physical systems. By exciting nonlinear dynamical systems and creating linear models from their state, we can create highly energy-efficient devices capable of solving machine learning tasks without building a modular system consisting of millions of neurons interconnected by synapses. To act as an effective reservoir, the chosen dynamical system must have two desirable properties: nonlinearity and memory. We present task agnostic spatial measures to locally measure both of these properties and exemplify them for a specific physical reservoir based upon magnetic skyrmion textures. In contrast to typical reservoir computing metrics, these metrics can be resolved spatially and in parallel from a single input signal, allowing for efficient parameter search to design efficient and high-performance reservoirs. Additionally, we show the natural trade-off between memory capacity and nonlinearity in our reservoir's behaviour, both locally and globally. Finally, by balancing the memory and nonlinearity in a reservoir, we can improve its performance for specific tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2108_01512 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Spatial Analysis of Physical Reservoir Computers Love, Jake Mulkers, Jeroen Msiska, Robin Bourianoff, George Leliaert, Jonathan Everschor-Sitte, Karin Machine Learning Disordered Systems and Neural Networks Other Condensed Matter Strongly Correlated Electrons Neural and Evolutionary Computing Physical reservoir computing is a computational framework that implements spatiotemporal information processing directly within physical systems. By exciting nonlinear dynamical systems and creating linear models from their state, we can create highly energy-efficient devices capable of solving machine learning tasks without building a modular system consisting of millions of neurons interconnected by synapses. To act as an effective reservoir, the chosen dynamical system must have two desirable properties: nonlinearity and memory. We present task agnostic spatial measures to locally measure both of these properties and exemplify them for a specific physical reservoir based upon magnetic skyrmion textures. In contrast to typical reservoir computing metrics, these metrics can be resolved spatially and in parallel from a single input signal, allowing for efficient parameter search to design efficient and high-performance reservoirs. Additionally, we show the natural trade-off between memory capacity and nonlinearity in our reservoir's behaviour, both locally and globally. Finally, by balancing the memory and nonlinearity in a reservoir, we can improve its performance for specific tasks. |
| title | Spatial Analysis of Physical Reservoir Computers |
| topic | Machine Learning Disordered Systems and Neural Networks Other Condensed Matter Strongly Correlated Electrons Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2108.01512 |