Bayesian Neural Network Series Post 1: Need for Bayesian Neural Networks

Figure 1: Network with point-estimates as weights vs Network with probability distribution as weights. Source

This post is the first post in an eight-post series of Bayesian Convolutional Networks. The posts will be structured as follows:

1. Need for Bayesian Neural Networks
2. Background knowledge needed to understand Bayesian Neural Networks better
3. Some recent work in the field of Bayesian Neural Networks
4. Bayesian Convolutional Neural Networks using Variational Inference
5. Build your own Bayesian Convolutional Neural Network in PyTorch
6. Uncertainty estimation in a Bayesian Neural Networks
7. Model Pruning in a Bayesian Neural Network
8. Applications in other areas (Super Resolution, GANs and so on..)

The blogs will be released every month starting first-week January 2020. Stay tuned! Also, feel free to check the post on ‘Why the World needs a Bayesian perspective’.

Let’s start this series by understanding the need for Bayesian Neural Networks in this blog.

Problem Statement