Neural Networks Are Impressively Good At Compression | Probably Dance

I’m trying to get into neural networks. There have been a couple big breakthroughs in the field in recent years and suddenly my side project of messing around with programming languages seemed short sighted. It almost seems like we’ll have real AI soon and I want to be working on that. While making my first couple steps into the field it’s hard to keep that enthusiasm. A lot of the field is still kinda handwavy where when you want to find out why something is used the way it’s used, the only answer you can get is “because it works like this and it doesn’t work if we change it.”

At least that’s my first impression. Still just dipping my toes in. But there is one thing I am very impressed with: How much data neural networks can express in how few connections.

To illustrate let me draw a very simple neural network. It’s not a very interesting neural network, I’m just connecting inputs to outputs.

Source: Neural Networks Are Impressively Good At Compression | Probably Dance