Computer Art Critique

• Network trained on 100 “good” images and 100 “bad” images

• Inputs are first 8000 bytes of gif file

• Network has 16 neurons

• A single output (can be + or -)

• Gives ~85% accuracy on training set (200 cases)

• Gives ~64% accuracy on out-of-sample data (different 200 cases)

Previous slide

Next slide

Back to first slide

View graphic version