VideosLearn & research
But what is a neural network?
3Blue1Brown explains layers, activations and weights through a network that recognizes handwritten digits.
The written adaptation by Josh Pullen of Grant Sanderson’s lesson follows a simple digit classifier from input pixels through layers to its output. It introduces weights and biases before the next lesson explains learning.
Start here if those terms are unfamiliar. Our exercise: sketch the input, one hidden layer and output, then distinguish an activation from a weight. This 2017 foundations example explains a simple network; it does not describe every modern architecture.
