Reservoir computing is a novel bio-inspired computing method, capable of solving complex tasks in a computationally efficient way. It has recently been successfully implemented using delayed feedback systems, allowing to reduce the hardware complexity of brain-inspired computers drastically. In this approach, the pre-processing procedure relies on the definition of a temporal mask which serves as a scaled time-mutiplexing of the input. Originally, random masks had been chosen, motivated by the random connectivity in reservoirs. This random generation can sometimes fail. Moreover, for hardware implementations random generation is not ideal due to its complexity and the requirement for trial and error. We outline a procedure to reliably construct an optimal mask pattern in terms of multipurpose performance, derived from the concept of maximum length sequences. Not only does this ensure the creation of the shortest possible mask that leads to maximum variability in the reservoir states for the given reservoir, it also allows for an interpretation of the statistical significance of the provided training samples for the task at hand.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3887384 | PMC |
| http://dx.doi.org/10.1038/srep03629 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Ultrafast silicon photonic reservoir computing engine delivering over 200 TOPS.
Nat Commun
December 2024
Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China.
Reservoir computing (RC) is a powerful machine learning algorithm for information processing. Despite numerous optical implementations, its speed and scalability remain limited by the need to establish recurrent connections and achieve efficient optical nonlinearities. This work proposes a streamlined photonic RC design based on a new paradigm, called next-generation RC, which overcomes these limitations.
View Article and Find Full Text PDFReservoir Stochastic Simulation Based on Octave Convolution and Multistage Generative Adversarial Network.
Sci Rep
December 2024
School of Computer and Information Engineering, Hubei Normal University, Huangshi, 435002, China.
For finely representation of complex reservoir units, higher computing overburden and lower spatial resolution are limited to traditional stochastic simulation. Therefore, based on Generative Adversarial Networks (GANs), spatial distribution patterns of regional variables can be reproduced through high-order statistical fitting. However, parameters of GANs cannot be optimized under insufficient training samples.
View Article and Find Full Text PDFCombining genomics and epidemiology to investigate a zoonotic outbreak of rabies in Romblon Province, Philippines.
Nat Commun
December 2024
Boyd Orr Centre for Population and Ecosystem Health, School of Biodiversity, One Health & Veterinary Medicine, College of Medical, Veterinary & Life Sciences, University of Glasgow, Glasgow, UK.
Rabies is a viral zoonosis that kills thousands of people annually in low- and middle-income countries across Africa and Asia where domestic dogs are the reservoir. 'Zero by 30', the global strategy to end dog-mediated human rabies, promotes a One Health approach underpinned by mass dog vaccination, post-exposure vaccination of bite victims, robust surveillance and community engagement. Using Integrated Bite Case Management (IBCM) and whole genome sequencing (WGS), we enhanced rabies surveillance to detect an outbreak in a formerly rabies-free island province in the Philippines.
View Article and Find Full Text PDFMultifunctional 2D FETs exploiting incipient ferroelectricity in freestanding SrTiO nanomembranes at sub-ambient temperatures.
Nat Commun
December 2024
Engineering Science and Mechanics, Penn State University, University Park, PA, USA.
Incipient ferroelectricity bridges traditional dielectrics and true ferroelectrics, enabling advanced electronic and memory devices. Firstly, we report incipient ferroelectricity in freestanding SrTiO nanomembranes integrated with monolayer MoS to create multifunctional devices, demonstrating stable ferroelectric order at low temperatures for cryogenic memory devices. Our observation includes ultra-fast polarization switching (~10 ns), low switching voltage (<6 V), over 10 years of nonvolatile retention, 100,000 endurance cycles, and 32 conductance states (5-bit memory) in SrTiO-gated MoS transistors at 15 K and up to 100 K.
View Article and Find Full Text PDFDecoding neuronal networks: A Reservoir Computing approach for predicting connectivity and functionality.
Neural Netw
December 2024
Department of Physics, University of Trento, Via Sommarive 14, Trento, 38123, TN, Italy.
In this study, we address the challenge of analyzing electrophysiological measurements in neuronal networks. Our computational model, based on the Reservoir Computing Network (RCN) architecture, deciphers spatio-temporal data obtained from electrophysiological measurements of neuronal cultures. By reconstructing the network structure on a macroscopic scale, we reveal the connectivity between neuronal units.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!