Artificial neural networks—algorithms inspired by connections in the brain—have “learned” to perform a variety of tasks, from pedestrian detection in self-driving cars, to analyzing medical images, to translating languages. Now, researchers at the University of California San Diego are training artificial neural networks to predict new stable materials.
“Predicting the stability of materials is a central problem in materials science, physics and chemistry,” said senior author Shyue Ping Ong, a nanoengineering professor at the UC San Diego Jacobs School of Engineering. “On one hand, you have traditional chemical intuition such as Linus Pauling’s five rules that describe stability for crystals in terms of the radii and packing of ions. On the other, you have expensive quantum mechanical computations to calculate the energy gained from forming a crystal that have to be done on supercomputers. What we have done is to use artificial neural networks to bridge these two worlds.”
By training artificial neural networks to predict a crystal’s formation energy using just two inputs—electronegativity and ionic radius of the constituent atoms—Ong and his team at the Materials Virtual Lab have developed models that can identify stable materials in two classes of crystals known as garnets and perovskites. These models are up to 10 times more accurate than previous machine learning models and are fast enough to efficiently screen thousands of materials in a matter of hours on a laptop. The team details the work in a paper published Sept. 18 in Nature Communications.
“Garnets and perovskites are used in LED lights, rechargeable lithium-ion batteries, and solar cells. These neural networks have the potential to greatly accelerate the discovery of new materials for these and other important applications,” noted first author Weike Ye, a chemistry Ph.D. student in Ong’s Materials Virtual Lab.
The team has made their models publicly accessible via a web application at http://crystals.ai. This allows other people to use these neural networks to compute the formation energy of any garnet or perovskite composition on the fly.
The researchers are planning to extend the application of neural networks to other crystal prototypes as well as other material properties.
Receive an email update when we add a new ARTIFICIAL NEURAL NETWORK article.
The Latest on: Artificial neural network
via Google News
The Latest on: Artificial neural network
Kalray Releases the Kalray Neural Network 3.0 (KaNN) to Accelerate Artificial Intelligence Application Development
on November 13, 2018 at 9:26 am
Kalray (Euronext Growth Paris – ALKAL), a pioneer in processors for new intelligent systems, today announced the launch of the Kalray Neural Network 3.0 (KaNN), a platform for Artificial Intelligence ... […]
Solarflare, Smart IOPS and Wistron Showcase High Performance NVMe over TCP Storage Appliance at Supercomputing 2018
on November 13, 2018 at 8:10 am
Solarflare is pioneering server connectivity for neural-class networks. From silicon to firmware to software ... solutions for use in ultra-scale applications in IoT, big data and artificial intellige... […]
New Nvidia T4 graphics chip lands on Google’s cloud and lots of servers
on November 12, 2018 at 4:41 pm
Graphics chips have become the standard for enabling artificial intelligence ... refers to the ability of neural networks to infer things from new data they’re presented with in real time ... […]
Neural Network market upcoming trends and industry analysis by 2023 examined in new market research report
on November 12, 2018 at 3:42 pm
Get the Sample Report: www.alliedmarketresearch.com/reque…26?utm_source=WTH Neural network is a form of artificial intelligence, which involves a series of algorithms used to understand the relationsh... […]
TYAN Highlights AMD EPYC™ Processor-Based HPC and Storage Server Platforms at SC18
on November 12, 2018 at 6:00 am
It is ideal for artificial intelligence, machine learning, and deep neural network training and inferencing workloads. Powered by dual AMD EPYC processors, TYAN’s Transport HX TN76A-B8242 can satisfy ... […]
This quirky experiment highlights AI's biggest challenges
on November 10, 2018 at 10:54 am
A neural network can quickly learn about a simple concept ... "These kinds of algorithms that today we're calling artificial intelligence are so simple and limited and hyper-focused on one task," she ... […]
Eta Compute Runs Neural Networks That Train Themselves
on November 8, 2018 at 11:06 am
But neural networks that do unsupervised learning are a better match ... “Eta Compute is not alone in addressing edge artificial intelligence, but [the company] is the first to offer an Arm-based MCU ... […]
Neural network accelerator for AI on the edge
on November 7, 2018 at 3:36 am
A new neural network accelerator specifically designed for artificial intelligence applications on edge devices has been launched via Crowd Supply providing a variety of different hardware priced from ... […]
Artificial Neural Networks. Beginners guide
on November 6, 2018 at 1:24 pm
Recent years were really signalized by the rise of the artificial intelligence, which is now proven to be the most monumental technology on the market. Not only computers are learning more and learnin... […]
via Bing News