MLG 032 Cartesian Similarity Metrics
Machine Learning Guide
00:00
The Difference Between Euclidean Distance and Dot Product Functions
The dot product is an arrow pointing from one point in vector space to another point. Sounds an awful lot like the euclidean distance, doesn't it? Indeed it does. And so you will see dot products used all over inside of neural networks,. So each neuron in a neural network will be, or at least contain, a dot product. A dot product lends itself better to computation when you're running your math on a gpu. It's more linear algebraic.
Transcript
Play full episode
