Featured Research

from universities, journals, and other organizations

New Insight Into How Bees See Could Improve Artificial Intelligence Systems

Date:
January 26, 2009
Source:
Monash University
Summary:
New research on bees could lead to improved artificial intelligence systems and computer programs for facial recognition.

Faces can dramatically change appearance when seen from different viewpoints, since the relationship between elements like nose and eyes change depending upon viewing angle. Bees solve this difficult visual problem by averaging previously learnt views.
Credit: Monash University

New research from Monash University bee researcher Adrian Dyer could lead to improved artificial intelligence systems and computer programs for facial recognition.

Dr Dyer is one of Australia's leading bee experts and his latest research shows that honeybees can learn to recognise human faces even when seen from different viewpoints.

Dr Dyer said the research could be applied in the areas of new technology, particularly the development of imaging systems.

"What we have shown is that the bee brain, which contains less than 1 million neurons, is actually very good at learning to master complex tasks. Computer and imaging technology programmers who are working on solving complex visual recognition tasks using minimal hardware resources will find this research useful," Dr Dyer said.

"Most current artificial intelligence (AI) recognition systems perform poorly at reliably recognising faces from different viewpoints. However the bees have shown they can recognise novel views of rotated faces using a mechanism of interpolating or image averaging previously learnt views."

The findings show that despite the highly constrained neural resources of the insects (their brains are 0.01 per cent the size of the human brain) their ability has evolved so that they're able to process complex visual recognition tasks.

The researchers individually trained different groups of free flying bees with a sugar reward for making correct choices, or alternatively the bees were punished with a bitter tasting solution for incorrect choices. Faces were presented on a vertical screen and bees slowly learnt to fly to the correct target faces. Over the course of a day a bee brain learned a complex task, and then when tested in non-rewarded tests (to totally excluded cues like olfaction) only bees that had experience multiple views (e.g. faces at both 0 and 60) were able to solve a novel rotational angle of 30.

Dr Dyer said the discovery helps to answer a fundamental question about how brains solve complex image rotational problems by either image averaging or mentally rotating previously learnt views.

"Bee brains clearly use image interpolation to solve the problem. In other words, bees that had learnt what a particular face looked like from two different viewpoints could then recognise a novel view of this target face. However, bees that had only learnt a single view could not recognise novel views," Dr Dyer said.

The study, performed over two years in Australia and Germany by Dr Dyer with the support of the US Air Force Office of Scientific Research (AFOSR), and Dr Quoc Vuong from Newcastle University UK, was published in the science journal PLoS ONE.

"The relationships between different components of the object often dramatically change when viewed from different angles but it is amazing to find the bees' brains have evolved clever mechanisms for problem solving which may help develop improved models for AI face recognition systems," Dr Dyer said.


Story Source:

The above story is based on materials provided by Monash University. Note: Materials may be edited for content and length.


Cite This Page:

Monash University. "New Insight Into How Bees See Could Improve Artificial Intelligence Systems." ScienceDaily. ScienceDaily, 26 January 2009. <www.sciencedaily.com/releases/2009/01/090123101211.htm>.
Monash University. (2009, January 26). New Insight Into How Bees See Could Improve Artificial Intelligence Systems. ScienceDaily. Retrieved July 25, 2014 from www.sciencedaily.com/releases/2009/01/090123101211.htm
Monash University. "New Insight Into How Bees See Could Improve Artificial Intelligence Systems." ScienceDaily. www.sciencedaily.com/releases/2009/01/090123101211.htm (accessed July 25, 2014).

Share This




More Plants & Animals News

Friday, July 25, 2014

Featured Research

from universities, journals, and other organizations


Featured Videos

from AP, Reuters, AFP, and other news services

Boy Attacked by Shark in Florida

Boy Attacked by Shark in Florida

Reuters - US Online Video (July 24, 2014) An 8-year-old boy is bitten in the leg by a shark while vacationing at a Florida beach. Linda So reports. Video provided by Reuters
Powered by NewsLook.com
Goma Cheese Brings Whiff of New Hope to DRC

Goma Cheese Brings Whiff of New Hope to DRC

Reuters - Business Video Online (July 24, 2014) The eastern region of the Democratic Republic of Congo, mainly known for conflict and instability, is an unlikely place for the production of fine cheese. But a farm in the village of Masisi, in North Kivu is slowly transforming perceptions of the area. Known simply as Goma cheese, the Congolese version of Dutch gouda has gained popularity through out the region. Ciara Sutton reports. Video provided by Reuters
Powered by NewsLook.com
Tyrannosaur Pack-Hunting Theory Aided By New Footprints

Tyrannosaur Pack-Hunting Theory Aided By New Footprints

Newsy (July 24, 2014) A new study claims a set of prehistoric T-Rex footprints supports the theory that the giant predators hunted in packs instead of alone. Video provided by Newsy
Powered by NewsLook.com
Bill Gates: Health, Agriculture Key to Africa's Development

Bill Gates: Health, Agriculture Key to Africa's Development

AFP (July 24, 2014) Health and agriculture development are key if African countries are to overcome poverty and grow, US software billionaire Bill Gates said Thursday, as he received an honourary degree in Ethiopia. Duration: 00:36 Video provided by AFP
Powered by NewsLook.com

Search ScienceDaily

Number of stories in archives: 140,361

Find with keyword(s):
Enter a keyword or phrase to search ScienceDaily for related topics and research stories.

Save/Print:
Share:

Breaking News:
from the past week

In Other News

... from NewsDaily.com

Science News

    Health News

      Environment News

        Technology News



          Save/Print:
          Share:

          Free Subscriptions


          Get the latest science news with ScienceDaily's free email newsletters, updated daily and weekly. Or view hourly updated newsfeeds in your RSS reader:

          Get Social & Mobile


          Keep up to date with the latest news from ScienceDaily via social networks and mobile apps:

          Have Feedback?


          Tell us what you think of ScienceDaily -- we welcome both positive and negative comments. Have any problems using the site? Questions?
          Mobile: iPhone Android Web
          Follow: Facebook Twitter Google+
          Subscribe: RSS Feeds Email Newsletters
          Latest Headlines Health & Medicine Mind & Brain Space & Time Matter & Energy Computers & Math Plants & Animals Earth & Climate Fossils & Ruins