Interval Methods for Seeking Fixed Points of Recurrent Neural Networks
| Autor: | Artur Wiliński, Bartłomiej Jacek Kubica, Paweł Hoser |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Automatic differentiation
Computer science 010103 numerical & computational mathematics 02 engineering and technology Fixed point Solver 01 natural sciences Stationary point Hopfield network Nonlinear system Recurrent neural network 0202 electrical engineering electronic engineering information engineering Interval (graph theory) 020201 artificial intelligence & image processing 0101 mathematics Algorithm |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783030504199 ICCS (3) |
| DOI: | 10.1007/978-3-030-50420-5_30 |
| Popis: | The paper describes an application of interval methods to train recurrent neural networks and investigate their behavior. The HIBA_USNE multithreaded interval solver for nonlinear systems and algorithmic differentiation using ADHC are used. Using interval methods, we can not only train the network, but precisely localize all stationary points of the network. Preliminary numerical results for continuous Hopfield-like networks are presented. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|