Researchers at the Tokyo Institute of Technology's Hasegawa Lab have developed a robot that is capable of thinking on its own and can learn how to solve problems it has never encountered before.
The Hasegawa group explains its SOINN (Self-Organizing Incremental Neural Network) artificial intelligence thus:
The SOINN is an unsupervised online-learning method, which is capable of incremental learning, based on Growing Neural Gas (GNG) and Self-Organizing Map (SOM). For online data that is non-stationary and has a complex distribution, it can approximate the distribution of input data and estimate appropriate the number of classes by forming a network in a self-organizing way.
"Thinking about artificial intelligence in the real world, actual environments are inevitably more complex, and they change quickly. So it's necessary to have a learning mechanism that adapts to the situation. Also, because new situations emerge, it's also necessary to have the ability to keep learning new information on the spot. As an algorithm for achieving that, we've created SOINN. SOINN is very light on computation, and it can learn while eliminating noise from the new information that comes in."
DigInfo adds that the SOINN robot model learns, not only through its own experiences, but also by tapping into the vast network of information on the Internet and via communication with other robots.
"One of the main problems with robots right now is that they are all designed for specific purposes," remarks George Wong of Ubergizmo. "A robot that assembles phones isn't going to wash the floor."
But what if robots could multitask? Those that make use of SOINN technology could potentially solve the problem of overly specialized robots.
According to SlashGear, however, there's no sign of when, or if, this new A.I. system will show up in commercial markets.
What are your thoughts about these super smart robots? Do you welcome the innovations or are they too alarming? Let us know in the comments (below).