Computers operate self-driving cars, pick friends’ faces out of photos on Facebook, and are learning to take on jobs typically entrusted only to human experts.
Researchers from the University of Wisconsin–Madison and Oak Ridge National Laboratory have trained computers to quickly and consistently detect and analyze microscopic radiation damage to materials under consideration for nuclear reactors. And the computers bested humans in this arduous task.
“Machine learning has great potential to transform the current, human-involved approach of image analysis in microscopy,” says Wei Li, who earned his master’s degree in materials science and engineering this year from UW–Madison.
Many problems in materials science are image-based, yet few researchers have expertise in machine vision — making image recognition and analysis a major research bottleneck. As a student, Li realized that he could leverage training in the latest computational techniques to help bridge the gap between artificial intelligence and materials science research.
Li, with Oak Ridge staff scientist Kevin Field and UW–Madison materials science and engineering professor Dane Morgan, used machine learning to make artificial intelligence better than experienced humans at analyzing damage to potential nuclear reactor materials. The collaborators described their approach in a paper published July 18 in the journal npj Computational Materials.
Machine learning uses statistical methods to guide computers toward improving their performance on a task without receiving any explicit guidance from a human. Essentially, machine learning teaches computers to teach themselves.
“In the future, I believe images from many instruments will pass through a machine learning algorithm for initial analysis before being considered by humans,” says Morgan, who was Li’s graduate school advisor.
The researchers targeted machine learning as a means to rapidly sift through electron microscopy images of materials that had been exposed to radiation, and identify a specific type of damage — a challenging task because the photographs can resemble a cratered lunar surface or a splatter-painted canvas.
That job, absolutely critical to developing safe nuclear materials, could make a time-consuming process much more efficient and effective.
“Human detection and identification is error-prone, inconsistent and inefficient. Perhaps most importantly, it’s not scalable,” says Morgan. “Newer imaging technologies are outstripping human capabilities to analyze the data we can produce.”
Previously, image-processing algorithms depended on human programmers to provide explicit descriptions of an object’s identifying features. Teaching a computer to recognize something simple like a stop sign might involve lines of code describing a red octagonal object.
More complex, however, is articulating all of the visual cues that signal something is, for example, a cat. Fuzzy ears? Sharp teeth? Whiskers? A variety of critters have those same characteristics.
Machine learning now takes a completely different approach.
“It’s a real change of thinking. You don’t make rules. You let the computer figure out what the rules should be,” says Morgan.
“This is just the beginning. Machine learning tools will help create a cyber infrastructure that scientists can utilize in ways we are just beginning to understand.”
Today’s machine learning approaches to image analysis often use programs called neural networks that seem to mimic the remarkable layered pattern-recognition powers of the human brain. To teach a neural network to recognize a cat, scientists simply “train” the program by providing a collection of accurately labeled pictures of various cat breeds. The neural network takes over from there, building and refining its own set of guidelines for the most important features.
Similarly, Morgan and colleagues taught a neural network to recognize a very specific type of radiation damage, called dislocation loops, which are some of the most common, yet challenging, defects to identify and quantify even for a human with decades of experience.
After training with 270 images, the neural network, combined with another machine learning algorithm called a cascade object detector, correctly identified and classified roughly 86 percent of the dislocation loops in a set of test pictures. For comparison, human experts found 80 percent of the defects.
“When we got the final result, everyone was surprised,” says Field, “not only by the accuracy of the approach, but the speed. We can now detect these loops like humans while doing it in a fraction of the time on a standard home computer.”
After he graduated, Li took a job with Google, but the research is ongoing. Morgan and Field are working to expand their training data set and teach a new neural network to recognize different kinds of radiation defects. Eventually, they envision creating a massive cloud-based resource for materials scientists around the world to upload images for near-instantaneous analysis.
“This is just the beginning,” says Morgan. “Machine learning tools will help create a cyber infrastructure that scientists can utilize in ways we are just beginning to understand.”
The Latest on: Machine learning tools
via Google News
The Latest on: Machine learning tools
- Machine Learning Experiments for Free with Google, Microsoft’s Python AutoML, Facebook’s Automated Debugging Tool, and more Resources! on September 17, 2018 at 3:02 pm
Google, Facebook, and Microsoft headline this week’s breakthrough-packed AVBytes weekly round-up! And we have a feeling it’s not the last time we’ll be saying that. 🙂 Highlights from the ... […]
- Machine learning technique to predict human cell organization published in nature methods on September 17, 2018 at 8:30 am
The prediction tool could also help scientists understand what goes ... limiting the technique's utility to study live cells and their dynamics. The machine learning approach would allow scientists to ... […]
- Microsoft (MSFT) Adds Deep Learning AI Tools with Lobe Buyout on September 17, 2018 at 6:20 am
Focus on Making AI Easy & Available For Use: Key Catalyst In a bid to integrate AI into its services, Microsoft is leaving no stone unturned to add innovative DL and machine learning (ML) tools. With ... […]
- Machine Learning May Prevent Defects in Metal 3D Printed Parts on September 17, 2018 at 5:51 am
Now, researchers are exploring machine learning to process the data obtained during 3D builds ... They scanned the part surfaces with a tool that generated 3D height maps, using that information to tr... […]
- Machine learning, knowledge management tools changing legal industry on September 13, 2018 at 3:34 pm
The legal profession, as with most other knowledge professions, is changing through the use of machine learning tools applied to ensure that legal information is leveraged and disseminated efficiently ... […]
- Senior machine learning scientist quits Google over plan to launch censored Chinese search tool on September 13, 2018 at 10:50 am
Jack Poulson was a senior research scientist at Google whose work on machine learning work was used to improve Google's search results; now he's quit the company over its Project Dragonfly, a once ... […]
- Google introduces machine learning analysis tool to combat AI bias on September 13, 2018 at 8:27 am
Google has unveiled a bias-detection feature for its TensorFlow machine learning web application, dubbed the What-If Tool, in a blog post. The What-If Tool allows users to view visualizations of model ... […]
- How machine learning and sensors are helping farmers boost yields on September 12, 2018 at 3:52 pm
That’s changing: emerging tools for data collection and analysis are helping boost yields and make farming more sustainable, according to Sam Eathington, chief science officer at the Climate Corporati... […]
- New HackerRank tool uses machine learning to help companies hire the best developers on September 12, 2018 at 6:31 am
Enterprises spend an average of more than $4,000 each year on recruiting, but lack strong data to measure how well they are hiring. On Wednesday, HackerRank launched the Tech Talent Matrix, a machine ... […]
via Bing News