![MiniRocket - podcast episode cover](https://static.libsyn.com/p/assets/c/4/0/0/c40080e8b200596dbafc7308ab683e82/angus_dempster.jpg)
Episode description
Angus Dempster, PhD Student at Monash University in Australia, comes on today to talk about MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification, a fast deterministic transform for time series classification. MINIROCKET reformulates ROCKET, gaining a 75x improvement on larger datasets with essentially the same performance. In this episode, we talk about the insights that realized this speedup as well as use cases.