WeightPrior

Paper

The Deep Weight Prior arXiv:1810.06943

We are going to reproduce considered in the paper experiments and prove (or disprove) that for dwp we have that

dwp improve the performance of Bayesian neural networks in case of limited data
initialization of weights with samples from dwp accelerates training of conventional convolutional neural networks, such that training procedure becomes faster than, say, in uniform initialization case, or in Xavier initialization case

run Auxiliary CNN Training with the command python get_kernels.py
run Experiments with the command runipy experiments.ipynb. You can install runipy via pip install runipy

Name		Name	Last commit message	Last commit date
Latest commit History 11 Commits
models		models
BMML_Project_Proposal.pdf		BMML_Project_Proposal.pdf
README.md		README.md
experiments.ipynb		experiments.ipynb
get_kernels.py		get_kernels.py
models.py		models.py