In 90 seconds, you can learn a large portion of the math behind how neural networks actually work. It is a very simplified picture, but let me show you the actual math. Every neural network has three kinds of layers: an input layer, one or more hidden layers, and an output layer. Each layer is made of neurons (the dots), connected by edges. Every edge carries its own weight: a single number. Your word or text input goes through a transformation into number form to enter the AI model. That transformation is called an embedding. In real models an embedding can be hundreds of numbers long; here I will use just two. Say the input is 5 and 2. Now give each edge a weight. To reach one neuron in the hidden layer, two edges feed into it: one with weight 10, one with weight 2. The neuron's value is 5 x 10 + 2 x 2, which is 50 + 4, so 54 (remember PEMDAS, my friends). The neuron beside it has its own edges, say weights 20 and 4. Its value is 5 x 20 + 2 x 4, which is 100 + 8, so 108. Multiply each input by the weight on its edge, add the results, and pass the number forward. Do it again for the next layer, and the next. Basically every generative AI model you use runs on this. One thing we are missing here: the nonlinear functions. They are crucial to neural networks, and I can make another video on those. The output layer also works a little differently from the hidden layers, and I will cover that in Part 2. I can also break down how these weights are actually learned, through backpropagation. If any of that interests you, or if I can do better somehow, let me know in the comments. Welcome!! I'm Harper. I've spent a decade building AI as a Stanford computer scientist, and now I hope to share the intuition I've developed with you. For a complete AI basics walkthrough, check out the link in my bio for my (free) video walkthrough guide. - @harpercarrollai