Скачать или смотреть Oscillatory State-Space Models: A New AI Framework | T. Konstantin Rusch | TEDxMIT

Oscillatory State-Space Models are a new class of AI algorithms inspired by cortical dynamics of the human brain. These models are exceptionally efficient, both in memory usage and computational speed. They are theoretically proven to learn sequential interactions of unlimited length and can approximate any causal operator between time series with arbitrary precision. Rooted in physics, Oscillatory State-Space Models offer an additional advantage: when applied to real-world robotic learning tasks, they produce representations that are not only accurate but also highly interpretable in a physical context.

AI, Big Data, Data Science, Machine Learning, Neuroscience, Robots T. Konstantin Rusch is a postdoctoral researcher at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL), working under the guidance of Professor Daniela Rus. He earned his Ph.D. in Applied Mathematics and Machine Learning from ETH Zurich, where he was advised by Professor Siddhartha Mishra. This talk was given at a TEDx event using the TED conference format but independently organized by a local community. Learn more at https://www.ted.com/tedx