Abstract
Inspired by the nonlinear dynamics of neural networks, new unconventional computing hardware has emerged under the name of physical reservoir computing. In this paradigm, an input-driven dynamical system (the reservoir) is exploited and trained to perform computational tasks. Recent spintronic thin-film reservoirs show state-of-the-art performances despite simplicity in their design. Here, we explore film geometry and show that simple changes to film shape and input location can lead to greater memory and improved performance across various time-series tasks.
Original language | English |
---|---|
Title of host publication | UCNC 2021: Unconventional Computation and Natural Computation |
Publisher | Springer |
Pages | 19 |
Number of pages | 34 |
Volume | 12984 |
ISBN (Electronic) | 978-3-030-87993-8 |
ISBN (Print) | 978-3-030-87992-1 |
DOIs | |
Publication status | Published - 11 Oct 2021 |
Event | Unconventional Computation and Natural Computation 2021 19th International Conference, UCNC 2021, Espoo, Finland, October 18–22, 2021 - Espoo, Finland, Espoo, Finland Duration: 18 Oct 2021 → 22 Oct 2021 Conference number: 19 |
Publication series
Name | LNTCS |
---|---|
Publisher | Springer |
Number | 1 |
Volume | 12984 |
Conference
Conference | Unconventional Computation and Natural Computation 2021 19th International Conference, UCNC 2021, Espoo, Finland, October 18–22, 2021 |
---|---|
Abbreviated title | UCNC 2021 |
Country/Territory | Finland |
City | Espoo |
Period | 18/10/21 → 22/10/21 |
Keywords
- magnetic thin films
- magnetic materials
- unconventional computing
- reservoir computing
- in-materio computing
- substrate geometry