artificial intelligence tagged posts

Photon-based processing units enable more Complex Machine Learning

The photonic tensor core performs vector-matrix multiplications by utilizing the efficient interaction of light at different wavelengths with multistate photonic phase change memories. CREDIT: Mario Miscuglio
The photonic tensor core performs vector-matrix multiplications by utilizing the efficient interaction of light at different wavelengths with multistate photonic phase change memories. CREDIT: Mario Miscuglio

Using photons to create more powerful and power-efficient processing units for artificial intelligence. Machine learning performed by neural networks is a popular approach to developing artificial intelligence, as researchers aim to replicate brain functionalities for a variety of applications.

A paper in the journal Applied Physics Reviews, by AIP Publishing, proposes a new approach to perform computations required by a neural network, using light instead of electricity...

Read More

Artificial Intelligence yields new Antibiotic

MIT researchers used a machine-learning algorithm to identify a drug called halicin that kills many strains of bacteria. Halicin (top row) prevented the development of antibiotic resistance in E. coli, while ciprofloxacin (bottom row) did not.

Image: courtesy of the Collins Lab at MIT

A deep-learning model identifies a powerful new drug that can kill many species of antibiotic-resistant bacteria

Using a machine-learning algorithm, MIT researchers have identified a powerful new antibiotic compound. In laboratory tests, the drug killed many of the world’s most problematic disease-causing bacteria, including some strains that are resistant to all known antibiotics. It also cleared infections in two different mouse models.

The computer model, which can screen more than a hundr...

Read More

Artificial Intelligence identifies previously unknown features associated with Cancer Recurrence

Illustration showing structure of the disk
Outline of the method. First, unsupervised deep neural networks were applied to pathology images without being taught any medical knowledge. Next, the features (a series of numbers that humans cannot directly understand) acquired by AI were translated into high-resolution images that can be understood by humans and were automatically assigned optimum weights to make images interpretable.

Artificial intelligence (AI) technology developed by the RIKEN Center for Advanced Intelligence Project (AIP) in Japan has successfully found features in pathology images from human cancer patients, without annotation, that could be understood by human doctors...

Read More

AI-designed Heat Pumps Consume Less Energy

Data-Driven Predesign Tool for Small-Scale Centrifugal Compressor in RefrigerationJournal of Engineering for Gas Turbines and Power, 2018; 140 (12) DOI: 10.1115/1.4040845

Researchers at EPFL have developed a method that uses artificial intelligence to design next-generation heat-pump compressors. Their method can cut the pumps’ power requirement by around 25%. In Switzerland, 50 – 60% of new homes are equipped with heat pumps. These systems draw in thermal energy from the surrounding environment – such as from the ground, air, or a nearby lake or river – and turn it into heat for buildings.

While today’s heat pumps generally work well and are environmentally friendly, they still have substantial room for improvement...

Read More