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
- Back to school: study justifies Nvidia’s push to arm students with deep learning laptopson July 31, 2022 at 8:00 am
As we approach that time of year again, students are gearing up to return to (or begin) their studies, and that means sales of the best student laptops are about to spike once more. I recently ...
- Analogue deep learning offers faster computation for artificial intelligence with much less energyon July 29, 2022 at 2:09 am
A multidisciplinary team of MIT researchers set out to push the speed limits of a type of human-made analogue synapse that they had previously developed. They utilized a practical inorganic material ...
- New hardware offers faster computation for artificial intelligence, with much less energyon July 28, 2022 at 12:08 pm
Researchers have created protonic programmable resistors -- the building blocks of analog deep learning systems -- that can process data 1 million times faster than the synapses in the human brain.
- Deep Learning Chip Market Robust Expansion is expected to 2030on July 28, 2022 at 3:51 am
Deep Learning Chip Market by Vendor Assessment, Technology Assessment, Partner & Customer Ecosystem, type solution, service, organization size, end-use verticals, and Region – Global Deep ...
- Using deep-learning algorithms to create maps of ship trackson July 26, 2022 at 7:42 am
A team of researchers affiliated with several universities in the U.S., working with the Goddard Space Flight Center, has used a deep-learning algorithm to create maps of ship tracks across the ...
- Deep learning technology enables faster and more accurate terahertz security inspectionon July 26, 2022 at 4:52 am
With the strengthening of global anti-terrorist measures, it is increasingly important to conduct security checks in public places to detect concealed objects carried on the human body.
- Adversarial attacks can cause DNS amplification, fool network defense systems, machine learning study findson July 25, 2022 at 4:33 am
New research shows how deep learning models trained for network intrusion detection can be bypassed. Recent years have seen a growing interest in the use of machine learning and d ...
- Deep learning for new alloyson July 20, 2022 at 11:23 pm
When is something more than just the sum of its parts? Alloys show such synergy. Steel, for instance, revolutionized industry by taking iron, adding a little carbon and making an alloy much stronger ...
- Deep learning delivers proactive cyber defenseon July 20, 2022 at 9:48 pm
No wonder an increasing number of organizations are beginning to explore how deep learning, and its ability to mimic the human brain, can outsmart and outpace the world’s fastest and dangerous ...
- PC build for deep learning under £4000on July 20, 2022 at 4:45 am
We walk you through building a PC that is capable of high performance deep learning AI and machine learning, without overspending. Deep learning, AI (Artificial Intelligence) and ML (Machine ...
via Bing News