Computer design capability similar to human learning – Times

Ed. Print NEW PROGRESS IN ARTIFICIAL INTELLIGENCE

Quite a technological feat that marks the beginning of an era in which machines will be able to learn from their environment as do people. – Abc Agency

Washington <- - end pub!> |

Scientists have developed a new computer model that mimics the ability of humans to learn new concepts, “one small step” more in the field of artificial intelligence, according to a study published in the specialized journal Science.

“What we want is to try to reduce the gap between learning ability of humans and machines (…). And discover why humans are so good at generalizing concepts, “said Joshua Tenenbaum, one of those responsible for the investigation, the Department of Cognitive Sciences at the Massachusetts Institute of Technology (MIT) in the United States.

Speed ​​and diversity

According to the study, the main virtue of human beings is their “speed” and “diversity” when learning new concepts and apply in new situations.

“A computer hard time generalizing from individual samples,” said Brenden Lake, New York University and senior author on a conference call to present the study.

Characters handwritten

The researchers focused on learning handwritten characters from different scripts and developed an algorithm that allow generalizations from a few examples.

“The computer does not have a program that applies to every situation, but rather a complex program of various learning programs, to suit every circumstance,” said Tenenbaum in the same conference.

When comparing the capacity of these computers face when learning tasks, including generation from examples seen only on a few occasions, with other computers and humans, characters checked how they outperformed their peers and matched to humans.

In many cases, the results of human cognitive and this new model, called “Bayesian Learning Program,” were “virtually indistinguishable”.

“In artificial intelligence no major findings. A set of good ideas that work. This is yet another, it is a small step, “said Lake.

For the researcher, proving” our work is that the principles of composition, causality and learn to understand will be critical to advance capabilities of the machines “.

computer model

Although the model can only, for now, learn the alphabet from handwritten characters, the underlying system could be expanded to build applications able to learn from others based on symbols, gestures, movements or systems languages, both written and spoken .

In fact, the computer model was able to classify, analyze and recreate handwritten characters and even managed to generate new alphabet letters “correct” appearance as the test of Touring type with which they are compared BPL results with human subjects who achieved the experiment.

How do you rate this story?

Average Rating
– points

.