{"id":150353,"date":"2022-11-16T08:24:02","date_gmt":"2022-11-16T14:24:02","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2022\/11\/mit-solved-a-century-old-differential-equation-to-break-liquid-ais-computational-bottleneck"},"modified":"2022-11-16T08:24:02","modified_gmt":"2022-11-16T14:24:02","slug":"mit-solved-a-century-old-differential-equation-to-break-liquid-ais-computational-bottleneck","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2022\/11\/mit-solved-a-century-old-differential-equation-to-break-liquid-ais-computational-bottleneck","title":{"rendered":"MIT solved a century-old differential equation to break \u2018liquid\u2019 AI\u2019s computational bottleneck"},"content":{"rendered":"

<\/a><\/p>\n

Last year, MIT developed an AI\/ML algorithm capable of learning and adapting to new information while on the job, not just during its initial training phase. These \u201cliquid\u201d neural networks<\/a> (in the Bruce Lee<\/a> sense) literally play 4D chess \u2014 their models requiring time-series data<\/a> to operate \u2014 which makes them ideal for use in time-sensitive tasks like pacemaker monitoring, weather forecasting, investment forecasting, or autonomous vehicle navigation. But, the problem is that data throughput has become a bottleneck, and scaling these systems has become prohibitively expensive, computationally speaking.<\/p>\n