DEC 26, 2018 10:29 PM PST

Advanced Computer System Based on Human Visual Learning

WRITTEN BY: Nouran Amin

In a study published in the Proceedings of the National Academy of Sciences, a team of researchers have engineered an advanced computer system by basing it on the same method of visual learning that humans use. This advanced type of technology is referred to as computer vision: the ability of computers to read and identify visual images. The study is a step closer to improving general artificial intelligent systems.

The “computer vision” system can identify objects based on only partial glimpses, like by using these photo snippets of a motorcycle. Credit: UCLA

Ideas were drawn from cognitive psychology and neuroscience in order to create framework for the development of the system. "Starting as infants, we learn what something is because we see many examples of it, in many contexts," explained principal investigator, Vwani Roychowdhury. "That contextual learning is a key feature of our brains, and it helps us build robust models of objects that are part of an integrated worldview where everything is functionally connected."

The system is made of three approaches. The first approach consists of the breaking of an image into small chunks which authors of the study refer to as "viewlets." The second approach is where the computer learns how the viewlets puzzle together to ultimately form an object in question. The last and third approach is how the computer interprets other objects in the surrounding area and it relevance to identifying the main object.

The “computer vision” system can identify objects based on only partial glimpses, like by using these photo snippets of a motorcycle. Credit: UCLA

Researchers immersed the new system in an internet replica of the human environment in order to assist in the learning process. They tested 9,000 images displaying people and other objects.

"Fortunately, the internet provides two things that help a brain-inspired computer vision system learn the same way humans do," says Roychowdhury. "One is a wealth of images and videos that depict the same types of objects. The second is that these objects are shown from many perspectives -- obscured, bird's eye, up-close -- and they are placed in different kinds of environments."

Source: UCLA Samueli School of Engineering, Science Daily

About the Author
  • Nouran earned her BS and MS in Biology at IUPUI and currently shares her love of science by teaching. She enjoys writing on various topics as well including science & medicine, global health, and conservation biology. She hopes through her writing she can make science more engaging and communicable to the general public.
You May Also Like
DEC 29, 2019
Space & Astronomy
DEC 29, 2019
The Dangers of Space Debris Explained
Humankind has become increasingly reliant on satellites and space technology to conduct everyday life, be it GPS for navigation on the road or satellite in...
JAN 01, 2020
Chemistry & Physics
JAN 01, 2020
Century-old Bretherton's Bubble Problem Solved
Some of the most common phenomena in life also hide puzzling mysteries.  When you pour water into a glass, many air bubbles would often appear. Becaus...
JAN 30, 2020
Chemistry & Physics
JAN 30, 2020
New Infrared Spectroscopic Method Grants Scientists Unprecedented "Seeing" Power
Infrared spectroscopy is a popular scientific method to identify and study molecules based on their absorption of infrared light. Scientists at the Max Pla...
FEB 06, 2020
Technology
FEB 06, 2020
3D Skin Printer Promotes Healing
Researchers at the University of Toronto Engineering, Sunnybrook developed a new handheld 3D printer that can deposit sheets of skin to cover large burn wo...
MAR 24, 2020
Neuroscience
MAR 24, 2020
Researchers Use Silicon to Record Electrical Signals Between Neurons
Researchers from Stanford University have created a way to connect the brain directly to silicon-based technologies. Hoping to assist the development of me...
MAR 23, 2020
Technology
MAR 23, 2020
Teaching your robot to do your chores
Would it not be great having a robot doing your chores? Well, researchers at MIT have designed a system that can training interactive robots to make our ho...
Loading Comments...