udibr / noisy_labels Public

Notifications You must be signed in to change notification settings
Fork 38
Star 118

TRAINING DEEP NEURAL-NETWORKS USING A NOISE ADAPTATION LAYER

118 stars 38 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 14 Commits
.gitignore		.gitignore
161103-run-plot.ipynb		161103-run-plot.ipynb
161202-run-plot-cifar100.ipynb		161202-run-plot-cifar100.ipynb
161230-run-plot-cifar100-sparse.ipynb		161230-run-plot-cifar100-sparse.ipynb
README.md		README.md
jacob-reed.py		jacob-reed.py
run.bash		run.bash
run_all.bash		run_all.bash
utils.py		utils.py

Repository files navigation

noisy_labels

TRAINING DEEP NEURAL-NETWORKS USING A NOISE ADAPTATION LAYER ICLR 2017 conference submission

Learning MNIST when almost half the labels are permuted in a fixed way. For example, when the task of labeling is split between two people that don’t agree.

Follow 161103-run-plot notebook for how to run the code.