Translate to multiple languages

Subscribe to my Email updates

https://feedburner.google.com/fb/a/mailverify?uri=helgeScherlundelearning
Enjoy what you've read, make sure you subscribe to my Email Updates

Sunday, December 03, 2017

Teaching machines to teach themselves | The Conversation - Machine learning

Photo: Arend Hintze
"For future machines to be as smart as we are, they'll need to be able to learn like we do" insist Arend Hintze, Assistant Professor of Integrative Biology & Computer Science and Engineering, Michigan State University.
 
How can computers learn to teach themselves new skills?
Photo: baza178/Shutterstock.com

Are you tired of telling machines what to do and what not to do? It’s a large part of regular people’s days – operating dishwashers, smartphones and cars. It’s an even bigger part of life for researchers like me, working on artificial intelligence and machine learning.

Much of this is even more boring than driving or talking to a virtual assistant. The most common way of teaching computers new skills – such as telling apart photos of dogs from ones of cats – involves a lot of human interaction or preparation. For instance, if a computer looks at a picture of a cat and labels it “dog,” we have to tell it that’s wrong.

But when that gets too cumbersome and tiring, it’s time to build computers that can teach themselves, and retain what they learn. My research team and I have taken a first step toward the sort of learning that people imagine the robots of the future will be capable of – learning by observation and experience, rather than needing to be directly told every little step of what to do. We expect future machines to be as smart as we are, so they’ll need to be able to learn like we do.

Setting robots free to learn on their own 
In the most basic methods of training computers, the machine can use only the information it has been specifically taught by engineers and programmers. For instance, when researchers want a machine to be able to classify images into different categories, such as telling apart cats and dogs, we first need some reference pictures of other cats and dogs to start with. We show these pictures to the machine, and when it guesses right we give positive feedback, and when it guesses wrong we apply negative feedback.

This method, called reinforcement learning, uses external feedback to teach the system to change its internal workings in order to guess better next time. This self-change involves identifying the factors that made the biggest differences in the algorithm’s decision, reinforcing accuracy and discouraging wrong decisions.

Another layer of advancement sets up another computer system to be the supervisor, rather than a human. This lets researchers create several dog-cat classifier machines, each with different attributes – perhaps some look more closely at color, while others look more closely at ear or nose shape – and evaluate how well they work. Each time each machine runs, it looks at a picture, makes a decision about what it sees and checks with the automated supervisor to get feedback.

Alternatively or in addition, we researchers turn off the classifier machines that don’t do as well, and introduce new changes to the ones that have done well so far. We repeat this many times, introducing small mutations into successive generations of classifier machines, slowly improving their abilities.

This is a digital form of Darwinian evolution – and it’s why this type of training is called a “genetic algorithm.” But even that requires a lot of human effort – and telling cats and dogs apart is an extremely simple task for a person.

Learning like people 
Our research is working toward a shift from a present in which machines learn simple tasks with human supervision, to a future in which they learn complicated processes on their own. This mirrors the development of human intelligence: As babies we were equipped with pain receptors that warned us about physical damage, and we had an instinct to cry when hungry or otherwise in need. 
Read more... 

Source: The Conversation