Abstract | ||
---|---|---|
In the present work, we investigate the possibility to expand existing Deep Learning solvers in order to improve the quality and stability of the training. We propose different new solvers, all of them based on the filtering of the neural network parameters, and experimentally prove that properly tuning their respective hyper-parameters leads to a clear improvement of the training and validation results, in quality and in stability. |
Year | Venue | Keywords |
---|---|---|
2018 | 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Deep Learning, optimization, gradient descent |
Field | DocType | ISSN |
Pattern recognition,Computer science,Filter (signal processing),Stochastic process,Linear programming,Artificial intelligence,Deep learning,Artificial neural network | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pierre Gillot | 1 | 0 | 0.34 |
J. Benois-Pineau | 2 | 103 | 12.35 |
Akka Zemmari | 3 | 171 | 26.35 |
Yurii Nesterov | 4 | 1800 | 168.77 |