The equivalence between lossless compression and artificial intelligence

By | November 2, 2006

Hutter Prize MedalDr. Marcus Hutter makes a very compelling argument for the equivalence between lossless compression and artificial intelligence. In fact, he has established the Hutter Prize that aims to discover the best compression algorithm for human knowledge. He is offering up to 50,000 Euros to the person who bests Alexander Ratushnyak’s paq8hp5 algorithm. The motivation behind this contest is that if one could develop a compressor that is better than the current state of the art, then invariably this compressor must be smarter.

“This compression contest is motivated by the fact that being able to compress well is closely related to acting intelligently, thus reducing the slippery concept of intelligence to hard file size numbers. In order to compress data, one has to find regularities in them, which is intrinsically difficult (many researchers live from analyzing data and finding compact models). So compressors beating the current “dumb” compressors need to be smart(er). Since the prize wants to stimulate developing “universally” smart compressors, we need a “universal” corpus of data. Arguably the online encyclopedia Wikipedia is a good snapshot of the Human World Knowledge. So the ultimate compressor of it should “understand” all human knowledge, i.e. be really smart. enwik8 is a hopefully representative 100MB extract from Wikipedia.”

Dr. Hutter has published a book advocating his theory behind a Universal Artificial Intelligence. In his book, he develops a theory that unifies active and passive reinforcement learning agents acting in unknown environments. His book is mathematical and information-theoretic so it would not be easily accessible by people with only a basic understanding of these areas. Regardless, if you think that you have what it takes and want to take a shot at winning 50,000 Euros then why not go for it?