Computer Sciences

A computational shortcut for neural networks

Neural networks are learning algorithms that approximate the solution to a task by training with available data. However, it is usually unclear how exactly they accomplish this. Two young Basel physicists have now derived ...

Engineering

Toe-tapping test evaluates fall risk in Parkinson's patients

Out of every 200 people, three live with Parkinson's disease. A progressive disorder that impacts the central nervous system and currently has no cure, Parkinson's disease can cause mobility issues, increasing patients' risk ...

Robotics

BirdBot is energy-efficient thanks to nature as a model

If a Tyrannosaurus Rex living 66 million years ago featured a similar leg structure as an ostrich running in the savanna today, then we can assume bird legs stood the test of time—a good example of evolutionary selection.

Machine learning & AI

Physical systems perform machine-learning computations

You may not be able to teach an old dog new tricks, but Cornell researchers have found a way to train physical systems, ranging from computer speakers and lasers to simple electronic circuits, to perform machine-learning ...

Automotive

Showing robots how to drive a car... in just a few easy lessons

Imagine if robots could learn from watching demonstrations: you could show a domestic robot how to do routine chores or set a dinner table. In the workplace, you could train robots like new employees, showing them how to ...

page 2 from 4