Digests » 70

ai

A.I.-Generated Adventure Game Rewrites Itself Every Time You Play

What would an adventure game designed by the world’s most dangerous A.I. look like? A neuroscience grad student is here to help you find out.

Reinforcement Learning: TicTacToe

Two agents play each other many times essentially starting at random but learning to beat each other, at least some of the time.

3D Ken Burns Effect from a Single Image

The Ken Burns effect allows animating still images with a virtual camera scan and zoom. Adding parallax, which results in the 3D Ken Burns effect, enables significantly more compelling results. Creating such effects manually is time-consuming and demands sophisticated editing skills. Existing automatic methods, however, require multiple input images from varying viewpoints. In this paper, we introduce a framework that synthesizes the 3D Ken Burns effect from a single image, supporting both a fully automatic mode and an interactive mode with the user controlling the camera.

Mistakes data scientists make

I’m fascinated by systems that use error to improve. These are Nassim Nicholas Taleb’s antifragile systems, which use error/pain/volatility/mistakes to improve. This is an observable paradox - a sign of a fundamental truth.

Learning Machine Learning

An online comics from Google AI.