24th European Conference on Artificial Intelligence, ECAI 2020

Mocanu, D. C. (Organiser)
Mocanu, E. (Organiser)
Tiago Pinto (Organiser)
Zita Vale (Organiser)

Datamanagement & Biometrics

Activity: Participating in or organising an event › Organising a conference, workshop, ...

Description

ECAI 2020 - Tutorial on Scalable Deep Learning: How far is one billion neurons?

Period	29 Aug 2020 → 8 Sep 2020
Event type	Conference
Conference number	24
Organisers	Centro Singular de Investigación En Tecnoloxías da Información (CiTIUS), Universidad de Santiago de Compostela
Degree of Recognition	International

Documents & Links

A fundamental task for artificial intelligence is learning. Deep Neural Networks have proven to cope perfectly with all learning paradigms, i.e. supervised, unsupervised, and reinforcement learning. Nevertheless, traditional deep learning approaches make use of cloud computing facilities and do not scale well to autonomous agents with low computational resources. Even in the cloud they suffer from computational and memory limitations and cannot be used to model properly large physical worlds for agents which assume networks with billion of neurons. These issues are addressed in the last few years by the emerging topic of scalable deep learning which makes use of static and adaptive sparse connectivity in neural networks before and throughout training. The tutorial covers these research directions focusing on theoretical advancements, practical applications, and hands-on experience, in two parts.