Search Results for author:
Found 2 papers, 2 papers with code
Recurrent Batch Normalization
We propose a reparameterization of LSTM that brings the benefits of batch normalization to recurrent neural networks.
Ranked #20 on
Language Modelling
on Text8
Knowledge Matters: Importance of Prior Information for Optimization
We explore the effect of introducing prior information into the intermediate level of neural networks for a learning task on which all the state-of-the-art machine learning algorithms tested failed to learn.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
