In this post I will demonstrate results from training neural nets using approximate Bayesian updating. The algorithm is described here, the code for everything can be found here. I will… Read more »
There’s a commonly repeated piece of wisdom about incremental improvement which says it’s important to know the difference between $1.01^x$ and $0.99^x$ as as $x$ gets very large. If you… Read more »
Here I propose a method for training neural networks using Bayesian updating. This method has a few advantages: Learns from just a single pass of the data Because it isn’t… Read more »