MIT Solved a Century-old Equation to Break the Computational Bottleneck Caused by ‘Liquid AI f.
MIT created an AI/ML algorithm that can learn and adapt to new information on the job last year. These “liquid” neural networks are literally 4D chess. Their models require time series data to function. This makes them perfect for time-sensitive tasks such as pacemaker monitoring, weather forecasting and investment forecasting. The problem is that the data throughput of these systems has become a bottleneck and scaling them has become prohibitively costly computationally.
Tuesday’s announcement by MIT researchers was that they had found a way to overcome this restriction. They did not expand the data pipeline but instead solved a differential equation that had been a puzzle for mathematicians ever since 1907. The team solved the differential equation that governs the interaction between two neurons via synapses… in order to unlock a new kind of efficient and fast artificial intelligence algorithm.
