- Category:
- Other systems
- Tags:
-
- File Size:
- 16.8mb
- Update:
- 2018-04-08
- Downloads:
- 0 Times
- Uploaded by:
- WG_JNU
Description: Based on the two level BP neural network, adding dropout and softmax, the output layer uses softmax to realize the recognition of handwritten character library MNIST, the accuracy rate is 90%.
To Search:
File list (Check if you may need any files):
| Filename | Size | Date |
|---|
| dropout_and_minibatch\DRELU.m | 171 | 2018-01-15
|
| dropout_and_minibatch\minibatch.asv | 4848 | 2018-01-31
|
| dropout_and_minibatch\minibatch.m | 4838 | 2018-01-30
|
| dropout_and_minibatch\MNISTdata.mat | 4403880 | 2018-01-15
|
| dropout_and_minibatch\mnist_all.mat | 13337300 | 2018-01-24
|
| dropout_and_minibatch\RELU.m | 40 | 2018-01-09
|
| dropout_and_minibatch\SOFTMAX.m | 54 | 2018-01-29
|
| dropout_and_minibatch | 0 | 2018-01-30 |
Download