This is my summer project at PML Group, where I worked on Bayesian Deep Learning. Generally, there are two kinds of uncertainties in Bayesian Deep Learning. One is called epistemic uncertainty (uncertainty about network weight) and the other is aleatoric uncertainties (uncertainty about input data). In my project, I extended the Linear and Conv layers in Pytorch with a flow-based stochastic part, so that the extended module could learn the distribution of input uncertainties by variational inferences.
This is the course project for CS-E5710 Bayesian Data Analysis, which I completed together with my friend Haoping Xiao.
Road traffic and safety have become one of the major problems in people’s safety concerns. According to 1, the annual road traffic deaths has reached 1.35 million in 2018, which makes road accident the leading killer of people aged from 5 to 29. In the UK, traffic accidents have caused more than 1700 deaths and more than 150,000 injuries in 2019 alone 2.