A carregar...

Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics

Recurrent neural networks (RNNs) are a widely used tool for modeling sequential data, yet they are often treated as inscrutable black boxes. Given a trained recurrent network, we would like to reverse engineer it–to obtain a quantitative, interpretable description of how it solves a particular task....

ver descrição completa

Na minha lista:
Detalhes bibliográficos
Publicado no:Adv Neural Inf Process Syst
Main Authors: Maheswaranathan, Niru, Williams, Alex H., Golub, Matthew D., Ganguli, Surya, Sussillo, David
Formato: Artigo
Idioma:Inglês
Publicado em: 2019
Assuntos:
Acesso em linha:https://ncbi.nlm.nih.gov/pmc/articles/PMC7416638/
https://ncbi.nlm.nih.gov/pubmed/32782423
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!