Speaker
Mr
Lukosevicius Mantas
(Jacobs University Bremen)
Description
Reservoir computing has emerged in the last decade as an alternative to gradient
descent methods for training recurrent neural networks. Echo State Network (ESN) is one of the key reservoir computing \ avors". While being practical, conceptually simple, and easy to implement, ESNs require some experience and insight to achieve the hailed good performance in many tasks. Here we present practical techniques and recommendations for successfully applying ESNs, as well as some more advanced application-speci?c modi?cations.
Author
Mr
Lukosevicius Mantas
(Jacobs University Bremen)