Machine learning

UTS researcher tests new mind-reading technology. Image: UTS

A portable, non-invasive system that can decode silent thoughts and turn them into text

Researchers are developing a way to incorporate uncertainty into machine learning systems

The experimental setup. The sensor sits atop the small glass box (left). A small amount of liquid containing VOCs (right) is added to the box, where it is drawn into the sensor via sniffing. (Credit: Aizenberg Lab/Harvard SEAS)

AI-enabled portable sensor can monitor air quality, identify spoiled food, and diagnose diseases

A wild New Caledonian crow (Corvus moneduloides) uses a stick tool to hunt for invertebrate prey – credit James St Clair

Using AI to open up the prospect of understanding what animals say to each other or of even initiating a conversation

An algorithm that teaches machines to learn without human supervision

A new test that can accurately identify multiple respiratory viruses within five minutes

(Image: Ritwik Kulkarni et al. 2023)

Tackling the illegal wildlife trade on the Internet with AI

Princeton researchers have found that human-language descriptions of tools can accelerate the learning of a simulated robotic arm lifting and using a variety of tools. Animation by the researchers; GIF by Neil Adelantar

Using words to teach robots

Could babies offer a new direction to overcome limitations of machine learning?

Credit: Unsplash/CC0 Public Domain

Predicting conduct disorder in kids using machine learning

Cutting the risk of death from sepsis dramatically with machine learning

Can machine learning really be fair and accurate?

Leveraging artificial intelligence and machine learning in our scientific instruments to unlock breakthrough discoveries

Could phase change materials help to save some of the trillions of gallons of water that power plants use for cooling?

A new electronic nose spotted cancer with up to 95 percent accuracy