label_noise_correction

Implementation of paper: Making Deep Neural Network Robust to Label Noise: a Loss Correction Approach.

Requirements:

Train all models and evaluate all the tests with: python experiment_mnist.py, or with bash script/run_experiment_mnist for faster training and testing. When this is finished, 4 files named backward.npy, backward_t.npy, cross_entropy.npy, forward.npy, forward_t.npy should have been created under the path ./result/mnist/.
Show the result with: python show_result_of_mnist_experiment.py.

This is the result of Fully connected network on MNIST. Notice that when N=0.5, the parametric matrix T is singular.

Name		Name	Last commit message	Last commit date
Latest commit History 23 Commits
cfg/experiments		cfg/experiments
helper		helper
network		network
script		script
trainer		trainer
README.md		README.md
__init__.py		__init__.py
experiment_mnist.py		experiment_mnist.py
results.png		results.png
show_result_of_mnist_experiment.py		show_result_of_mnist_experiment.py