differential

Last year, MIT developed an AI/ML algorithm that can learn and adapt to new information while on the job, not just during its initial training phase. These “liquid” (in Bruce Lee’s sense) neural networks literally play 4D chess – their models requiring time-series data to operate – making them ideal for use in time-sensitive tasks …

MIT has solved a century-old differential equation to break the computational bottleneck of ‘liquid’ AI | Engadget Read More »