Semantic segmentation - labelling each pixel in an image to a specific class- models require large amounts of manually labeled and collected data to train.

The authors develop and test a machine learning algorithm for predicting diabetes diagnoses.

In this study the authors looked at the ability of artificial intelligence to detect tempo, rhythm, and intonation of a piece played on violin. Technology such as this would allow for students to practice and get feedback without the need of a teacher.

In this study, potential physiological effects of Red 40 food dye, found in many different food products, are tested using Daphnia magna, a small freshwater crustacean.

In this study, a deep learning model is used to classify post-traumatic stress disorder patients through novel markers to assist in finding candidate biomarkers for the disorder.

The authors use pictures of candy wrappers and neural networks to improve nutritional accuracy of diet-tracking apps.

In this article, the authors investigate the RNA expression differences between groups of chronic cocaine abusers and drug-free subjects.

The authors develop a new method for training machine learning algorithms to differentiate between hate speech and cultural speech in online platforms.

In this study, the authors hypothesized that closed-circuit television images could be stored with improved resolution by using enhanced deep residual (EDSR) networks.

Sound waves can be amazingly powerful, especially when they work together. Here the authors create an “acoustic lens” that focuses sound waves on a single location. This makes the sound waves very powerful, capable of causing damage at a precise point. In the future, acoustic lenses like this could potentially be used to treat cancer by killing small tumors without surgery.