Artificial neural networks

Perceptron

One of the oldest applications of artificial intelligence is based on the simulation of animal nerve cells (neurons). Neural networks are made up of many interconnected components, and they are capable of some computational activity, although the neurons that make up these networks are usually quite simplified, compared to those that are part of the nervous system of human beings and other animals.

This type of application has been the subject of multiple exaggerations and unusual predictions. These networks have been said to be capable of solving the most difficult problems, NP-complete problems, like the traveling salesman problem, and similar ones. A normal program can solve these problems, but the time needed grows exponentially as a function of the size of the problem, while a neural network can solve them in a short time. To some extent this is true, provided that we bear in mind that the solution obtained is not necessarily the best, but only an approximation, which is often sufficient for our needs.

Automatic Learning

By popculturegeek.com
 Originally posted to Flickr as Comic-Con 2004
Terminator statue, CC BY 2.0
https://commons.wikimedia.org

As I said in a previous article, automatic learning is one of the areas of weak artificial intelligence which has been object of research for at least 40 years. Strictly speaking, rather than a field of application, automatic learning is a methodology or technique used by other fields of application, such as neural networks, expert systems or data analysis. Automatic learning is divided into two main branches:

• Supervised automatic learning, which has been used most frequently up to now. This post is dedicated to explain it.
• Unsupervised automatic learning, related to the field usually called Data Mining. It has lately been widely advertised by the media in relation to a program (AlphaGo Zero) that, learning by itself, has reached a level comparable to the world champion of the game called Go (at the end of this post I’ll talk more about this).

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.