The Role of Structure and Complexity on Reservoir Computing Quality

Dale, Matthew; Dewhirst, Jack Daniel; O’Keefe, Simon; Sebald, Angelika; Stepney, Susan; Trefzer, Martin A.

doi:10.1007/978-3-030-19311-9_6

Cited by 8 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Highly-structured networks, such as a lattice, more accurately model the material crystal structure. Lattice networks with recurrent connections have be shown to be dynamically similar to less restrictive recurrent neural networks, but often have to compensate with larger network size [31,32,33].…”

Section: Resultsmentioning

confidence: 99%

Reservoir Computing with Thin-film Ferromagnetic Devices

Dale,

Evans,

Jenkins

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Advances in artificial intelligence are driven by technologies inspired by the brain, but these technologies are orders of magnitude less powerful and energy efficient than biological systems. Inspired by the nonlinear dynamics of neural networks, new unconventional computing hardware has emerged with the potential for extreme parallelism and ultra-low power consumption. Physical reservoir computing demonstrates this with a variety of unconventional systems from optical-based to spintronic [1]. Reservoir computers provide a nonlinear projection of the task input into a highdimensional feature space by exploiting the system's internal dynamics. A trained readout layer then combines features to perform tasks, such as pattern recognition and time-series analysis. Despite progress, achieving state-of-the-art performance without external signal processing to the reservoir remains challenging. Here we show, through simulation, that magnetic materials in thin-film geometries can realise reservoir computers with greater than or similar accuracy to digital recurrent neural networks. Our results reveal that basic spin properties of magnetic films generate the required nonlinear dynamics and memory to solve machine learning tasks. Furthermore, we show that neuromorphic hardware can be reduced in size by removing the need for discrete neural components and external processing. The natural dynamics and nanoscale size of magnetic thin-films present a new path towards fast energy-efficient computing with the potential to innovate portable smart devices, self driving vehicles, and robotics.

show abstract

Section: Resultsmentioning

confidence: 99%

Reservoir Computing with Thin-film Ferromagnetic Devices

Dale,

Evans,

Jenkins

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The input connections are chosen uniformly from the interval [−1, 1]. All of these structures, including the simpler ring topology, are capable of performing nontrivial tasks [1,4,16].…”

Section: Noise In Esnmentioning

confidence: 99%

Quantifying Robustness and Capacity of Reservoir Computers with Consistency Profiles

Lymburn

Jüngling

Small

2020

Artificial Neural Networks and Machine Learning – ICANN 2020

View full text Add to dashboard Cite

We study the consistency property in reservoir computers with noise. Consistency quantifies the functional dependence of a driven dynamical system on its input via replica tests. We characterise the highdimensional profile of consistency in typical reservoirs subject to intrinsic and measurement noise. An integral of the consistency is introduced to measure capacity and act as an effective size of the reservoir. We observe a scaling law in the dependency of the consistency capacity on the noise amplitude and reservoir size, and demonstrate how this measure of capacity explains performance.

show abstract

“…To demonstrate the concept, CHARC has been used to compare different simulated network topologies of varying complexities as an analogy for material design (Dale et al, 2019a). Using CHARC, the dynamical limitations and boundaries of different structures are characterised.…”

Section: Substrate Designmentioning

confidence: 99%