A research team at Osaka University created a system that uses a convolutional neural network to learn the features distinguishing different cancer cells, based on images from a phase-contrast microscope. This system accurately differentiated human and mouse cancer cells, as well as their radioresistant clones. This novel approach can improve the speed and accuracy of cancer diagnosis by avoiding the laboriousness and potential errors associated with equivalent analyses by humans.
Geckos are amazingly agile. In addition to running across land and up trees, the animals can prance across the surface of water. A new study reveals how they do it.
Producing realistic animated film figures is a highly complex technical endeavour. ETH researchers have now shown how drones can be used to greatly reduce the effort required in the process.
A new paper provides a comprehensive look at the development of an ethical framework, code of conduct, and value-based design methodologies for AI researchers and application developers in Europe. The 'Barcelona Declaration for the Proper Development and Usage of Artificial Intelligence in Europe' was launched in the spring of 2017 at the B-Debate event in Barcelona, to stimulate further discussion among policy makers, industry leaders, researchers and application developers on AI's opportunities and risks in the current 'gold rush' environment.
Using precise brain measurements, Yale researchers predicted how people's eyes move when viewing natural scenes, an advance in understanding the human visual system that can improve a host of artificial intelligence efforts, such as the development of driverless cars.
Argentine and Spanish researchers have used statistical techniques of automatic learning to analyze mobility patterns and technology of the hunter-gatherer groups that inhabited the Southern Cone of America, from the time they arrived about 12,000 years ago until the end of the 19th century. Big data from archaeological sites located in the extreme south of Patagonia have been used for this study.
The constant movement of fish that seems random is actually precisely deployed to provide them at any moment with the best sensory feedback they need to navigate the world.
Researchers trained a deep neural network to classify wildlife species using 3.37 million camera-trap images of 27 species of animals obtained from five states across the United States. The model then was tested on nearly 375,000 animal images at a rate of about 2,000 images per minute on a laptop computer, achieving 97.6 percent accuracy -- likely the highest accuracy to date in using machine learning for wildlife image classification
Researchers at the Nara Institute of Science and Technology, IMAGICA GROUP Inc. and OLM Digital, Inc. report the world's first technique for automatic colorization focused on Japanese anime production. The new technique is expected to promote efficiency and automation in anime production.
Big data from human medical studies combined with analytical approaches from physics of complex dynamic systems offer a whole new way to understand and defeat aging.