Poster
Learning Hierarchical Information Flow with Recurrent Neural Modules
Danijar Hafner · Alexander Irpan · James Davidson · Nicolas Heess

Mon Dec 4th 06:30 -- 10:30 PM @ Pacific Ballroom #105 #None
in Posters Mon »

We propose ThalNet, a deep learning model inspired by neocortical communication via the thalamus. Our model consists of recurrent neural modules that send features through a routing center, endowing the modules with the flexibility to share features over multiple time steps. We show that our model learns to route information hierarchically, processing input data by a chain of modules. We observe common architectures, such as feed forward neural networks and skip connections, emerging as special cases of our architecture, while novel connectivity patterns are learned for the text8 compression task. Our model outperforms standard recurrent neural networks on several sequential benchmarks.

Keywords: Model Selection and Structure Learning · Memory-Augmented Neural Networks · Recurrent Networks

Author Information

Danijar Hafner (Google Brain & UCL)
Alexander Irpan (Google)
James Davidson (Google Brain)
Nicolas Heess (Google DeepMind)

More from the Same Authors