How Liquid Neural Networks Could Boost Ai Capabilities

Researchers from the Massachusetts Institute of Technology (MIT) have developed a new form of machine learning called liquid neural networks. These networks are easily adaptable and flexible, even after training, and could be used in robotics and autonomous transport. A test was conducted using a drone, which was able to fly autonomously in an unknown environment without incident. Liquid neural networks could be used in robotics for machines operating in unknown or dangerous environments, and in autonomous vehicles to help them adapt to difficult weather conditions or unforeseen, dangerous situations.