MIT’s new ‘liquid’ neural network learns on the job — so robots can adapt to changing conditions

MIT researchers have invented an adaptive “liquid” neural network that could improve decision-making in self-driving cars and medical diagnosis. The algorithm adjusts to changes experienced by real-world systems by changing their underlying equations as they receive new data. “This is a way forward for the future of robot control, natural language processing, video processing — any form of time series data processing,” said Ramin Hasani, the study paper’