Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

This AI birdwatcher lets you 'see' through the eyes of a machine

01.11.2019

New research aims to open the 'black box' of computer vision

It can take years of birdwatching experience to tell one species from the next. But using an artificial intelligence technique called deep learning, Duke University researchers have trained a computer to identify up to 200 species of birds from just a photo.


A Duke team trained a computer to identify up to 200 species of birds from just a photo. Given a photo of a mystery bird (top), the A.I. spits out heat maps showing which parts of the image are most similar to typical species features it has seen before.

Credit: Chaofan Chen, Duke University

The real innovation, however, is that the A.I. tool also shows its thinking, in a way that even someone who doesn't know a penguin from a puffin can understand.

The team trained their deep neural network -- algorithms based on the way the brain works -- by feeding it 11,788 photos of 200 bird species to learn from, ranging from swimming ducks to hovering hummingbirds.

The researchers never told the network "this is a beak" or "these are wing feathers." Given a photo of a mystery bird, the network is able to pick out important patterns in the image and hazard a guess by comparing those patterns to typical species traits it has seen before.

Along the way it spits out a series of heat maps that essentially say: "This isn't just any warbler. It's a hooded warbler, and here are the features -- like its masked head and yellow belly -- that give it away."

Duke computer science Ph.D. student Chaofan Chen and undergraduate Oscar Li led the research, along with other team members of the Prediction Analysis Lab directed by Duke professor Cynthia Rudin.

They found their neural network is able to identify the correct species up to 84% of the time -- on par with some of its best-performing counterparts, which don't reveal how they are able to tell, say, one sparrow from the next.

Rudin says their project is about more than naming birds. It's about visualizing what deep neural networks are really seeing when they look at an image.

Similar technology is used to tag people on social networking sites, spot suspected criminals in surveillance cameras, and train self-driving cars to detect things like traffic lights and pedestrians.

The problem, Rudin says, is that most deep learning approaches to computer vision are notoriously opaque. Unlike traditional software, deep learning software learns from the data without being explicitly programmed. As a result, exactly how these algorithms 'think' when they classify an image isn't always clear.

Rudin and her colleagues are trying to show that A.I. doesn't have to be that way. She and her lab are designing deep learning models that explain the reasoning behind their predictions, making it clear exactly why and how they came up with their answers. When such a model makes a mistake, its built-in transparency makes it possible to see why.

For their next project, Rudin and her team are using their algorithm to classify suspicious areas in medical images like mammograms. If it works, their system won't just help doctors detect lumps, calcifications and other symptoms that could be signs of breast cancer. It will also show which parts of the mammogram it's homing in on, revealing which specific features most resemble the cancerous lesions it has seen before in other patients.

In that way, Rudin says, their network is designed to mimic the way doctors make a diagnosis. "It's case-based reasoning," Rudin said. "We're hoping we can better explain to physicians or patients why their image was classified by the network as either malignant or benign."

###

The team is presenting a paper on their findings at the Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019) in Vancouver on December 12.

Other authors of this study include Daniel Tao and Alina Barnett of Duke and Jonathan Su at MIT Lincoln Laboratory.

CITATION: "This Looks Like That: Deep Learning for Interpretable Image Recognition," Chaofan Chen, Oscar Li, Daniel Tao, Alina Barnett, Jonathan Su and Cynthia Rudin. Electronic Proceedings of the Neural Information Processing Systems Conference. December 12, 2019.

Media Contact

Robin Ann Smith
ras10@duke.edu
919-681-8057

 @DukeU

http://www.duke.edu

Robin Ann Smith | EurekAlert!
Further information:
https://today.duke.edu/2019/10/ai-birdwatcher-lets-you-see-through-eyes-machine

More articles from Information Technology:

nachricht A Memory Effect at Single-Atom Level
04.11.2019 | Max-Planck-Institut für die Physik des Lichts

nachricht High-resolution radar sensors and AI for safe autonomous driving – project AuRoRaS
31.10.2019 | Deutsches Forschungszentrum für Künstliche Intelligenz GmbH, DFKI

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: A Memory Effect at Single-Atom Level

An international research group has observed new quantum properties on an artificial giant atom and has now published its results in the high-ranking journal Nature Physics. The quantum system under investigation apparently has a memory - a new finding that could be used to build a quantum computer.

The research group, consisting of German, Swedish and Indian scientists, has investigated an artificial quantum system and found new properties.

Im Focus: Shedding new light on the charging of lithium-ion batteries

Exposing cathodes to light decreases charge time by a factor of two in lithium-ion batteries.

Researchers at the U.S. Department of Energy's (DOE) Argonne National Laboratory have reported a new mechanism to speed up the charging of lithium-ion...

Im Focus: Visible light and nanoparticle catalysts produce desirable bioactive molecules

Simple photochemical method takes advantage of quantum mechanics

Northwestern University chemists have used visible light and extremely tiny nanoparticles to quickly and simply make molecules that are of the same class as...

Im Focus: An amazingly simple recipe for nanometer-sized corundum

Almost everyone uses nanometer-sized alumina these days - this mineral, among others, constitutes the skeleton of modern catalytic converters in cars. Until now, the practical production of nanocorundum with a sufficiently high porosity has not been possible. The situation has changed radically with the presentation of a new method of nanocorundum production, developed as part of a German-Polish cooperation of scientists from Mülheim an der Ruhr and Cracow.

High temperatures and pressures, processes lasting for even dozens of days. Current methods of producing nanometer-sized alumina, a material of significant...

Im Focus: Structured light promises path to faster, more secure communications

Quantum mechanics is embracing patterns of light to create an alphabet that can be leveraged to build a light-based quantum network

Structured light is a fancy way to describe patterns or pictures of light, but deservedly so as it promises future communications that will be both faster and...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

VideoLinks
Industry & Economy
Event News

Smart lasers open up new applications and are the “tool of choice” in digitalization

30.10.2019 | Event News

International Symposium on Functional Materials for Electrolysis, Fuel Cells and Metal-Air Batteries

02.10.2019 | Event News

NEXUS 2020: Relationships Between Architecture and Mathematics

02.10.2019 | Event News

 
Latest News

The secret behind crystals that shrink when heated

04.11.2019 | Physics and Astronomy

Worldwide observations confirm nearby 'lensing' exoplanet

04.11.2019 | Physics and Astronomy

A new material for regenerative medicine capable to control cell immune response

04.11.2019 | Health and Medicine

VideoLinks
Science & Research
Overview of more VideoLinks >>>