Skip to content

Neural network comparative study for the optical recognition task

Notifications You must be signed in to change notification settings

mougharik/neuralNetStudy

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Neural Network Comparative Study

Comparing various architectures (fully-connected and multiple convolutional variants) on the USPS dataset for the optical recognition task. Currently, four different weight initialization presets are available for training the models: effective, too slow, too fast, and default. In addition to weight initialization schemes, various learning rates have been tested and categorized in a similar manner (effective, too slow, too fast). Please refer to the materials folder for a more detailed write-up.

Example Usage

python3 study.py --net 1    # fully-connected net
python3 study.py --net 2    # locally-connected CNN
python3 study.py --net 3    # fully-connected CNN

python3 study.py --net 1 --init 1   # effective learning
python3 study.py --net 1 --init 2   # fast learning
python3 study.py --net 1 --init 3   # slow learning

todo

  • add visualization functionality for kernel filters and activations for each layer
  • add options for dropout, momentum, and bagging

About

Neural network comparative study for the optical recognition task

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages