Understanding backward() in PyTorch (Updated for V0.4)
Update for PyTorch 0.4:
Earlier versions used Variable to wrap tensors with different properties. Since version 0.4, Variable is merged with tensor, in other words, Variable is NOT needed anymore. The flag require_grad can be directly set in tensor. Accordingly, this post is also updated.
Bayesian basics I - the way of reasoning
One day after lunch, one of my colleagues spotted a man running outside of our windows where there is a fire escape balcony along the outside of our building. We immediately realized that he was probably a thief since we occasionally had heard of people from other labs losing expensive computers after seeing a man on the fire escape balcony. We ...
10 post articles, 2 pages.