Ricerca di contatti, progetti,
corsi e pubblicazioni

RNNAIssance - RNNAIssance

Persone

 

Schmidhuber J.

(Responsabile)

Rauber P.

(Collaboratore)

Schlag I.

(Collaboratore)

van Steenkiste S.

(Collaboratore)

Zuo X.

(Collaboratore)

Abstract

Real brains are still superior to our award-winning Recurrent Neural Networks (RNNs) in many ways: They learn a predictive model of their initially unknown environment, and somehow use it for abstract planning and reasoning. They continually build on earlier acquired skills, becoming more and more general problem solvers able to deal with many diverse and complex tasks. Guided by Algorithmic Information Theory, we will build a revolutionary RNN-based AI (RNNAI) that does the same.

Informazioni aggiuntive

Acronimo
RNNAIssance
Data d'inizio
01.11.2016
Data di fine
29.02.2020
Durata
39 Mesi
Enti finanziatori
SNSF
Stato
Concluso
Categoria
Swiss National Science Foundation / Project Funding / Mathematics, Natural and Engineering Sciences (Division II)