Skip to content

A little experiment with the simplest possible network, visualizing gradiant descent

Notifications You must be signed in to change notification settings

bimtauer/Neural-Net-Regressor

Repository files navigation

Binder

Neural-Net-Regressor

A little experiment with the simplest possible network, visualizing gradiant descent

I got inspired by James Loy's NN tutorial and adapted it into an even simpler network with only one node that performs a simple linear regression. The point for me was to visualize the loss surface corresponding to weight and bias of the single node and plotting the models learning steps.

About

A little experiment with the simplest possible network, visualizing gradiant descent

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published