Your browser doesn't support javascript.
loading
Input-to-State Representation in Linear Reservoirs Dynamics.
IEEE Trans Neural Netw Learn Syst ; 33(9): 4598-4609, 2022 09.
Article em En | MEDLINE | ID: mdl-33651697
ABSTRACT
Reservoir computing is a popular approach to design recurrent neural networks, due to its training simplicity and approximation performance. The recurrent part of these networks is not trained (e.g., via gradient descent), making them appealing for analytical studies by a large community of researchers with backgrounds spanning from dynamical systems to neuroscience. However, even in the simple linear case, the working principle of these networks is not fully understood and their design is usually driven by heuristics. A novel analysis of the dynamics of such networks is proposed, which allows the investigator to express the state evolution using the controllability matrix. Such a matrix encodes salient characteristics of the network dynamics; in particular, its rank represents an input-independent measure of the memory capacity of the network. Using the proposed approach, it is possible to compare different reservoir architectures and explain why a cyclic topology achieves favorable results as verified by practitioners.
Assuntos

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Redes Neurais de Computação Tipo de estudo: Prognostic_studies Idioma: En Revista: IEEE Trans Neural Netw Learn Syst Ano de publicação: 2022 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Redes Neurais de Computação Tipo de estudo: Prognostic_studies Idioma: En Revista: IEEE Trans Neural Netw Learn Syst Ano de publicação: 2022 Tipo de documento: Article