What is Solomonoff Induction?
Solomonoff induction is a mathematically rigorous, idealized form of induction, that is, predicting what will happen in the future based on prior experiences. It is a part of algorithmic information theory. This induction scheme is theoretically optimal, i.e., given enough data, it will always be able to assign probabilities to future events with the maximum possible accuracy allowed. The only problem with Solomonoff induction is that it is incomputable, that is, it would require a computer with infinite processing power to run. However, all successful inductive schemes and machines — including animals and humans — are approximations of Solomonoff induction. Every verbal argument containing advice for better induction, to the extent that it actually works, works by coaxing the listener into modifying his or her inductive strategy in such a way that it better approximates Solomonoff induction. The idea that induction can be mathematically formalized in this way is quite profound, and
