Artificial intelligence (AI) is considered one of the key technologies for our future society. Computer programs imitate human abilities such as logical thinking, learning, planning and creativity. But how does that actually work? How can a machine learn? Like in many others, the founda- tions for this technology are in mathematics. This exhibit allows to explore some basic mechanisms and principles.

Try out gradient descent in a treasure hunt in the ocean. Train and adapt a neural network for the recognition of handwritten numbers. Let a robot find its way through a maze and think about best strategies on how to perform best in unknown situations.

Gradient descent: Two ships send probes to the sea floor to find a treasure that is located at the deepest point of the sea floor. What is the fastest way to find it?


Program "Reinforcement Learning": A robot learns to find its way through a maze.