Skip to content

Latest Updates in Digital Intelligence: Top Trending News Highlights

AI Predictions for Star Planets and Disease Detection for Data Science Novices Highlight Week of June 22-28, 2019

Latest Data News Highlights: A Compilation of Topical Insights
Latest Data News Highlights: A Compilation of Topical Insights

In the realm of scientific discovery, researchers and engineers continue to push the boundaries of what is possible with machine learning (ML) and artificial intelligence (AI). Here are some of the latest breakthroughs that have caught our attention.

Firstly, a groundbreaking algorithm has been developed by researchers at the University of Texas at Austin. This algorithm can estimate the likelihood of stars having planets orbiting them, a significant step forward in our understanding of the cosmos. Similarly, a team from the Southwest Research Institute and several U.S. universities have created an algorithm that predicts the same with an impressive 90% probability for 360 stars.

The prediction of celestial bodies is not the only area where AI is making strides. Researchers from MIT and Brown University have developed an interactive tool called VDS. This tool, designed for users with little data science experience, can generate machine learning models for a variety of tasks. For instance, a user can input a dataset concerning the metabolic rates, ages, and disease occurrence of patients, and the tool can then predict whether future patients will develop diseases based on their metabolic rate and age. The VDS tool can also generate predictive models for tasks such as predicting sales revenue.

AI is also proving to be a valuable tool in the medical field. A system developed by the Pentagon can analyze a person's heartbeat and identify them by their heartbeat signature from up to 200 meters away. This system, which uses lasers to detect the surface movement caused by a heartbeat, can detect heartbeats through regular clothing but not thick clothing. Moreover, a neural network has been developed that can identify individuals with up to 95 percent accuracy, a potential game-changer for patient monitoring in the future.

The advancements in AI are not limited to earthly applications. A neural network, trained on 8,000 traditional universe simulations, has been developed to teach it how particles interact. Given the direction and distance particles should be moving as the universe expands, the neural network can create simulations with relatively few errors. Furthermore, the neural network has been trained on a catalog of thousands of stars, their chemical compositions, and orbiting planets, enabling it to build 3D simulations of the structural formation of the universe in milliseconds, a process that usually takes days.

Lastly, the researchers and engineers that created the MLPerf benchmark suite have developed benchmarks for image recognition, object detection, and translation. These benchmarks will test how well a machine learning system can predict a label for a given image, detect an object in an image, and translate sentences between English and German.

These advancements in AI and machine learning are just the tip of the iceberg. As these technologies continue to evolve, we can expect to see even more remarkable breakthroughs in the future.

Read also:

Latest