Thursday, November 16, 2017

What is artificial intelligence

Hal 9000, from the film 2001 a Space Odyssey
Terms such as smart and artificial intelligence are being abused lately. Let’s look at some recent news that have appeared in various media:
  • Smart benches with solar energy free mobile charge, and access to Wi-Fi. These public street benches, installed in London by Ford, incorporate a Wi-Fi repeater and a solar plate that gives them power to charge a mobile phone battery. Where is the intelligence in the bench? Nowhere. The intelligence belongs to the human being who invented these devices. In a similar case, we would be saying that our houses are smart because they have electricity and an Internet connection.
  • China implements smart trash cans. In this case the waste bin also incorporates a solar panel connected to a mobile phone charger. In the future they will also have a Wi-Fi repeater and a device to disinfect the garbage with ultraviolet rays. As in the previous case, the mere presence of an electrical or electronic device is confused with intelligence.
  • Goodyear tests a tire that predicts when it must be changed. The tire has a built-in wireless sensor that detects when it needs to be replaced and issues the corresponding warning. Although this case is somewhat more complex than the previous two, something is again called smart when it isn’t. To implement this, you just need a sensor and a simple electronic device, more or less equivalent to those radio devices that since decades have been incorporated to wild animals, to follow their displacements and watch their activities.
As you can see, what is now called smart is just what was formerly called automatic. But of course, the word smart is more appealing, that’s why it’s being abused. In the same way, there is a tendency to call artificial intelligence what formerly was called computer science.

John McCarthy
What is artificial intelligence? The term was invented in 1956 by John McCarthy, during a seminar that took place in Dartmouth College, Hanover, U.S.A. Blinded by the recent advances in computer design, the attendees to the seminar predicted that in ten years smart programs would be available that would defeat the world chess champion, together with other programs that would make perfect translations between any two human languages. The first objective was achieved, not ten, rather forty years later; the second has not been achieved yet (see another article in this blog).
The most accepted definition of artificial intelligence during the first decades of its history was the following:
A computer program that processes symbolic information heuristically.
Symbolic information is not strictly numerical information. For example, texts; or the symbolic representation of the positions of the pieces on a chessboard. Heuristics means relying on experience, rather than using pre-established algorithms.
There are two very different types of artificial intelligence:
  1. Weak artificial intelligence: a set of applications researched for decades, where interesting advances have been made. I will mention some:
    • Automatic theorem proving
    • Games usually considered intelligent
    • Processing of texts written in a human language (including automatic translation)
    • Image recognition
    • Expert systems
    • Neural networks
    • Smart agents
    • Automatic learning
  1. Strong artificial intelligence: this is the real artificial intelligence, the construction of machines capable of competing with man, not in just one concrete activity (like playing chess), but in many. This branch of artificial intelligence is not yet feasible, although the media, plus a few so-called experts, have been spreading false information and announcing its imminent birth since thirty years ago.

In the next post, I will discuss when real experts predict that we can expect to get a true strong artificial intelligence.

Manuel Alfonseca

No comments:

Post a Comment