Using artificial intelligence to smell the roses

A pair of researchers at the University of California, Riverside, has used machine learning to understand what a chemical smells like — a research breakthrough with potential applications in the food flavor and fragrance industries. “We now can use artificial intelligence to predict how any chemical is going to smell to humans,” said Anandasankar Ray,

New machine learning method allows hospitals to share patient data — privately

To answer medical questions that can be applied to a wide patient population, machine learning models rely on large, diverse datasets from a variety of institutions. However, health systems and hospitals are often resistant to sharing patient data, due to legal, privacy, and cultural challenges. An emerging technique called federated learning is a solution to

US Air Force uses Senvol software to develop multi-laser 3D printing applications

The US Air Force is using Senvol’s data-driven machine learning software for additive manufacturing (AM), to enable the production of large-scale aerospace parts using multi-laser 3D printing technology. Utilizing an EOS powder bed fusion (LPBF) 3D printer, the program is focused on developing baseline mechanical properties and design allowables, to optimize the production of end-use

Google Simplifies ML Kit SDK, Adds APIs

Google has made a standalone version of its Machine Learning Kit SDK available to developers, allowing them to create AI-assisted apps directly on devices. The big change includes two new APIs that make it possible to create web-connected ML Kit apps without requiring Firebase. Google first debuted ML Kit at I/O two years ago. Since

For university classrooms, are telepresence robots the next best thing to being there?

Telepresence robots help university students learning remotely to feel more a part of the class, new research by Oregon State University suggests. The findings are particularly important given the nationwide shift to online instruction caused by the COVID-19 pandemic, forcing many students who otherwise would be in classrooms and labs to pursue their education from

Researchers use drones, machine learning to detect dangerous ‘butterfly’ landmines

Using advanced machine learning, drones could be used to detect dangerous “butterfly” landmines in remote regions of post-conflict countries, according to research from Binghamton University, State University at New York. Researchers at Binghamton University had previously developed a method that allowed for highly accurate detection of “butterfly” landmines using low-cost commercial drones equipped with infrared

OpenVINO: Intel’s Deep Learning Toolkit

This toolkit enables you to deploy deep learning tools like OpenCV across diverse types of Intel hardware, using a consistent API and publicly available models (or your own). Talk to CPUs, GPUs, FPGAs, the Neural Compute Stick 2, and more, in C, C++, or Python. Download OpenVINO: Learn more: // // //

AI techniques in medical imaging may lead to incorrect diagnoses

Machine learning and AI are highly unstable in medical image reconstruction, and may lead to false positives and false negatives, a new study suggests. A team of researchers, led by the University of Cambridge and Simon Fraser University, designed a series of tests for medical image reconstruction algorithms based on AI and deep learning, and

AI techniques used to improve battery health and safety

Researchers have designed a machine learning method that can predict battery health with 10x higher accuracy than current industry standard, which could aid in the development of safer and more reliable batteries for electric vehicles and consumer electronics. The researchers, from Cambridge and Newcastle Universities, have designed a new way to monitor batteries by sending

Introducing Edge Impulse: Free for Developers

Create new intelligent devices with embedded machine learning! With TinyML, Edge Impulse makes it easy to collect and process data, then train, test, and deploy your own models, all from one simple interface. Plus, its "unit testing" features enable you to re-train models to add features without losing accuracy. The system includes free access for