We are excited to announce that the repository will soon undergo an upgrade, featuring a new look and feel along with several enhanced features to improve your experience. Please be on the lookout for further updates and announcements regarding the launch date. We appreciate your support and look forward to unveiling the improved platform soon.
dc.contributor.author | Manjunath, Gandhi![]() |
|
dc.date.accessioned | 2022-04-04T04:40:25Z | |
dc.date.available | 2022-04-04T04:40:25Z | |
dc.date.issued | 2022-06 | |
dc.description.abstract | Recurrent neural networks (RNNs) are successfully employed in processing information from temporal data. Approaches to training such networks are varied and reservoir computing-based attainments, such as the echo state network (ESN), provide great ease in training. Akin to many machine learning algorithms rendering an interpolation function or fitting a curve, we observe that a driven system, such as an RNN, renders a continuous curve fitting if and only if it satisfies the echo state property. The domain of the learned curve is an abstract space of the left-infinite sequence of inputs and the codomain is the space of readout values. When the input originates from discrete-time dynamical systems, we find theoretical conditions under which a topological conjugacy between the input and reservoir dynamics can exist and present some numerical results relating the linearity in the reservoir to the forecasting abilities of the ESNs. | en_ZA |
dc.description.department | Mathematics and Applied Mathematics | en_ZA |
dc.description.librarian | hj2022 | en_ZA |
dc.description.uri | https://ieeexplore.ieee.org/servlet/opac?punumber=5962385 | en_ZA |
dc.identifier.citation | G. Manjunath, "An Echo State Network Imparts a Curve Fitting," in IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 6, pp. 2596-2604, doi: 10.1109/TNNLS.2021.3099091. | en_ZA |
dc.identifier.issn | 2162-237X (online) | |
dc.identifier.issn | 2162-2388 (print) | |
dc.identifier.other | 10.1109/TNNLS.2021.3099091 | |
dc.identifier.uri | http://hdl.handle.net/2263/84771 | |
dc.language.iso | en | en_ZA |
dc.publisher | Institute of Electrical and Electronics Engineers | en_ZA |
dc.rights | © 2021 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. | en_ZA |
dc.subject | Recurrent neural network (RNN) | en_ZA |
dc.subject | Echo state network (ESN) | en_ZA |
dc.subject | Task analysis | en_ZA |
dc.subject | Reservoirs | en_ZA |
dc.subject | Training | en_ZA |
dc.subject | Mathematical model | en_ZA |
dc.subject | Dynamical systems | en_ZA |
dc.subject | Neurons | en_ZA |
dc.subject | Curve fitting | en_ZA |
dc.subject | Echo state property (ESP) | en_ZA |
dc.subject | Learning | en_ZA |
dc.subject | Nonautonomous dynamical systems | en_ZA |
dc.title | An echo state network imparts a curve fitting | en_ZA |
dc.type | Postprint Article | en_ZA |