Neural Networks Demystified: Part 1
summary
Shows how to build a working neural regressor in Python and NumPy to predict test score from hours studied and slept, scaling inputs to [0,1], using exactly two inputs and one output and training on only three recorded examples, then fitting a network with one hidden layer with three units and sigmoid activation. Demonstrates the code and forward/backprop steps and produces predictions that fit the tiny dataset but are obviously limited by the minimal training examples.
AI-written summary · about
related talks
01h 25mBuilding & Optimization of Neural Networks from Scratch with Numpy
01h 50mNeural Networks: Walkthrough
56mA Gentle Introduction to Neural Networks and making your own with Python
25mIntroduction to Neural Networks
43m(Deep) Learn You a Neural Net for Great Good!
43mA Gentle Introduction to Neural Networks
58mNeural Networks: A Primer
36mNeural Networks