November 15, 2017

From The Economist (on AlphaGo Zero):

After a single day it was playing at the level of an advanced professional. After two days it had surpassed the performance of the version that beat Mr Lee in 2016.

From Nature (H/T: Kevin Lewis):

A long-standing goal of artificial intelligence is an algorithm that learns, tabula rasa, superhuman proficiency in challenging domains. Recently, AlphaGo became the first program to defeat a world champion in the game of Go. The tree search in AlphaGo evaluated positions and selected moves using deep neural networks. These neural networks were trained by supervised learning from human expert moves, and by reinforcement learning from self-play. Here we introduce an algorithm based solely on reinforcement learning, without human data, guidance or domain knowledge beyond game rules. AlphaGo becomes its own teacher: a neural network is trained to predict AlphaGo’s own move selections and also the winner of AlphaGo’s games. This neural network improves the strength of the tree search, resulting in higher quality move selection and stronger self-play in the next iteration. Starting tabula rasa, our new program AlphaGo Zero achieved superhuman performance, winning 100–0 against the previously published, champion-defeating AlphaGo.

From Harper's:

The B.M.I. of American men rises following marriage and falls following divorce.

From Harper's:

Advanced paternal age contributes to geekiness in male children.

From The Guardian (Antonia Fraser on "My writing day"):

I have never worked after dinner since 1968 when I was writing Mary Queen of Scots and my then husband [Hugh Fraser] was away in his constituency. I took the opportunity to work until 4am. When I read it through in the morning, it was total rubbish. This taught me a sharp lesson.