neural-net-learns-without-backprop. This project implements a basic neural network from scratch that learns through random weight adjustments rather than traditional backpropagation. The network attempts to learn a simple addition operation.

github.com/echohive42/neural-net-learns-without-backprop

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

No recent activity.