,
6 tweets,
2 min read
Read on Twitter
Deep Learning (DL circa 2012) big breakthrough is that it demonstrated a new kind of Artificial Intuition. Prior to DL, computers provided programmable Artificial Logic (circa 1945).
AlphaGo big breakthrough is that it demonstrated that with the use of DL one could beat the best human in a game of intuition (i.e. Go). .
AlphaZero big breakthrough is that you could train a system from scratch (without human knowledge) and it could be the best human system Stockfish that was programmed using logic. medium.com/intuitionmachi…
The fundamental discovery of AlphaZero is that with enough intuition (or amortized inference) one can best even a very good logic system. It is a construction proof of how human beings just with intuition can perform logical reasoning.
In this construction proof, we discover that play - self-play in the case of AlphaZero - is a critical ingredient to developing new knowledge. Knowledge creation requires play and self-play is automated knowledge creation.
But how do we bridge the gap between knowledge discovery and knowledge invention? One cannot invent without a generative model: medium.com/intuitionmachi… #deeplearning #ai
