Details

Autor(en) / Beteiligte

• Schmidhuber, Jürgen

Titel

Deep learning in neural networks: An overview

Ist Teil von

• Neural networks, 2015-01, Vol.61, p.85-117

Ort / Verlag

United States: Elsevier Ltd

Erscheinungsjahr

2015

Link zum Volltext

Quelle

Elsevier ScienceDirect Journals Complete

Beschreibungen/Notizen

• In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.