Learning Hierarchical Information Flow with Recurrent Neural Modules
Abstract
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.
Cite
Text
Hafner et al. "Learning Hierarchical Information Flow with Recurrent Neural Modules." Neural Information Processing Systems, 2017.Markdown
[Hafner et al. "Learning Hierarchical Information Flow with Recurrent Neural Modules." Neural Information Processing Systems, 2017.](https://mlanthology.org/neurips/2017/hafner2017neurips-learning/)BibTeX
@inproceedings{hafner2017neurips-learning,
title = {{Learning Hierarchical Information Flow with Recurrent Neural Modules}},
author = {Hafner, Danijar and Irpan, Alexander and Davidson, James and Heess, Nicolas},
booktitle = {Neural Information Processing Systems},
year = {2017},
pages = {6724-6733},
url = {https://mlanthology.org/neurips/2017/hafner2017neurips-learning/}
}