With AlphaGo, DeepMind demonstrated the power of machine-learning to beat humans. And it is not only in games where we come up short
Put simply, AI refers to technologies that try to replicate core human functions. Peet van Biljon, formerly of McKinsey and now one of the leading innovation specialists engaging with the topic, sums it up neatly: “It’s about computers doing things ever smarter than we used to expect of machines, and ever closer to what we thought only humans could do.” The resemblance to human intelligence is no coincidence, he says, as “recent advances all involve some sort of neural network, which is modelled on how we think the human brain works.”
At the heart of the excitement over AI is the concept of machine learning: computers working things out for themselves without being explicitly programmed to do so. Instead, they progress by processing and analysing huge amounts of data, identifying patterns and improving their performance as they do so.
The classic example is the AlphaGo system, developed by Google-owned DeepMind, which in 2017 beat the reigning (human) world champion of the game Go. Impressive in itself, this became more so when a second machine, AlphaGo Zero, which had merely been programmed with the game’s rules, trained itself to play without any human prompting at all, and within six weeks had learned...