NIPS 2015 Workshops
Some notes from attending the NIPS 2015 workshops:
-
Jacob Andreas, Dan Klein, Alignment-Based Compositional Semantics for Instruction Following
-
Jürgen Schmidhuber, On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models
-
Martin Arjovsky, Amar Shah, Yoshua Bengio, Unitary Evolution Recurrent Neural Networks
-
Risi Kondor, parallel Multiresolution Matrix Factorization
-
Tian Wang, Kyunghyun Cho, Larger-Context Language Modelling
-
Armand Joulin, Tomas Mikolov, Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets