Multi-Path Summation: The Σ a Single-Output Network Hides
Going from 1 output neuron to 2 adds one step to backpropagation. That step is not a new rule — the multivariable chain rule had it all along.
Tags03
#LLM
Gradients and Backpropagation: Three Rounds with One Cat
A 2→2→1 network, and where every single number in three rounds of training comes from. Plus two things you only see once you actually run it.
What a Neural Network Actually Is: A Function with 13,002 Parameters
Starting from handwritten digit recognition: what neurons, layers, weights, biases and activation functions each are, and why the whole network is only a function.