Regularizing Neural Networks by Stochastically Training Layer Ensembles

November 21, 2019 ยท Declared Dead ยท ๐Ÿ› International Workshop on Machine Learning for Signal Processing

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Alex Labach, Shahrokh Valaee arXiv ID 1911.09669 Category cs.LG: Machine Learning Cross-listed stat.ML Citations 2 Venue International Workshop on Machine Learning for Signal Processing Last Checked 4 months ago
Abstract
Dropout and similar stochastic neural network regularization methods are often interpreted as implicitly averaging over a large ensemble of models. We propose STE (stochastically trained ensemble) layers, which enhance the averaging properties of such methods by training an ensemble of weight matrices with stochastic regularization while explicitly averaging outputs. This provides stronger regularization with no additional computational cost at test time. We show consistent improvement on various image classification tasks using standard network topologies.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted