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.
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 Latest on: Deep learning
via Google News
The Latest on: Deep learning
- Analysis on North America's Deep Learning Chipset Industry, 2019-2025: Anticipating a CAGR of 35.4%on March 21, 2020 at 8:33 am
The "North America Deep Learning Chipset Market, by Type, by Technology, by End User, by Country, Industry Analysis and Forecast, 2019 - 2025" report has been added to ResearchAndMarkets.com's ...
- Deep Learning Predicts Stroke-Lesion Changes at 1 Weekon March 20, 2020 at 6:47 am
A deep learning algorithm is comparable or even superior to common clinical measures for predicting infarct size and location up to a week following acute ischemic stroke, new research suggests.
- Global Deep Learning Chipset Market by Type, Technology, End-user and Region - Forecast to 2025on March 19, 2020 at 12:36 pm
Dublin, March 19, 2020 -- The "Global Deep Learning Chipset Market, by Type, by Technology, by End User, by Region, Industry Analysis and Forecast, 2019 - 2025" report.
- North American Deep Learning Chipset Market by Type, Technology, End-user and Country - Forecast to 2025on March 19, 2020 at 5:53 am
Research and Markets also offers Custom Research services providing focused, comprehensive and tailored research.
- Hybrid AI systems are quietly solving the problems of deep learningon March 19, 2020 at 3:54 am
Deep learning, the main innovation that has renewed interest in artificial intelligence in the past years, has helped solve many critical problems in computer vision, natural language processing, and ...
- Test-time augmentation for deep learning-based cell segmentation on microscopy imageson March 19, 2020 at 3:10 am
Recent advancements in deep learning have revolutionized the way microscopy images of cells are processed. Deep learning network architectures have a large number of parameters, thus, in order to ...
- Automatic optic nerve head localization and cup-to-disc ratio detection using state-of-the-art deep-learning architectureson March 19, 2020 at 3:08 am
Computer vision has greatly advanced recently. Since AlexNet was first introduced, many modified deep learning architectures have been developed and they are still evolving. However, there are few ...
- Deep learning changes scientific research, finds antibiotic for multi-resistant bacteriaon March 18, 2020 at 12:55 pm
Scientists at MIT and Harvard’s Broad Institute and MIT’s CSAIL built a deep learning network that can acquire a broad representation of molecular structure and thereby discover novel antibiotics.
- Deep Learning Market Size Record Booming 51.1% CAGR by 2020 to 2026on March 18, 2020 at 4:22 am
The global Deep Learning market is analyzed to grow at a CAGR of around 51.1% during the forecast period and projected to reach the market value over US$ 56,427.2 Mn in 2027. The study provides an ...
- MIT’s deep learning found an antibiotic for a germ nothing else could killon March 13, 2020 at 1:14 pm
Scientists at the Massachusetts Institute of Technology and Harvard last month described in the scholarly journal Cell how they used a deep learning neural network to identify a molecular compound ...
via Bing News