Version 1, last updated by humel at April 22, 2010 19:58 UTC
Denoising Convolutional Network
Objectif
- Illustrate experimentaly the advantage of convolutional networks for image recognition over traditional deep MLP (with or without unsupervised pretraining).
- Benchmark the model on the NIST dataset using the results obtained by Sylvain Pannetier to select the best training strategy
Experiences
SETUP
| Convolutional Layers ([nb_filters,x_size,y_size]) | ([52,5,5], [32,3,3]) , ([52,7,7], [52,3,3]) |
| number hidden units (MLP) | (1000),(500) |
| Maxpool |
([2,2],[2,2]) |
| Corruption level | ([0.2,0.1]) |
| Minibatch size | (100) |
| Number epoch pretrain /layer | (10) |
| Pretrain learning rate | (0.01) |
| Finetune learning rate | (0.1),(0.01) |
| Pretraining Dataset | (P07) |
| Finteuning Dataset | (P07) |
Results
Experiences currently running.