Image Painting using Artificial Neural Networks

This experiment treats the pixels of an image as a learning problem: it takes the (x,y) position on a grid and learns to predict the color at that point using regression to (r,g,b).



Back to Labs.

Choose your own image:

Original Image
Neural Network output


Learning rate:
The learning rate should be decreased over time (slide left) to let the neural network better overfit the training data. It's nice to not have to worry about overfitting.


Original Image here


Back to Labs.