The Most Important Deep Learning Math Concept

We discuss the dot product, and why it’s the most fundamental linear algebra concept for Neural Networks, and go over an example with a perceptron and a self-attention transformer. If you enjoy learning about Math for Deep Learning, check out these two videos I made on the Vector Calculus behind Gradient Descent: TIMESTAMPS: 0:00 - Intro 0:28 - What is the Dot Product 1:22 - Perceptron example 4:48 - Perceptron with 3 features 6:13 - Self Attention Transformers