Magnus Ross
@magnusar.bsky.social
Postdoc at UCL AI Center. Currently work on: forecasting, uncertainty quantification, antimicrobial resistance. Previously: Gaussian processes, physics informed ML, trading power.
https://magnusross.github.io
https://magnusross.github.io
The seminar will happen at the UCL AI Centre in the 90 High Holborn building
July 8, 2025 at 2:19 PM
The seminar will happen at the UCL AI Centre in the 90 High Holborn building
it's the dream blogging crossover!
July 7, 2025 at 4:04 PM
it's the dream blogging crossover!
great post, please do more like it :)
July 3, 2025 at 4:34 PM
great post, please do more like it :)
Reposted by Magnus Ross
What news editors and politicians think people want: "Just tell them they'll get a tram somewhere in their city if they're nice."
What people really want: "SHOW ME THE FULL GPS ROUTE PLAN COMPLETE WITH LINKS TO THE WIKIPEDIA PAGES OF THE DISUSED RAILWAY LINES THAT COULD COME BACK INTO USE."
What people really want: "SHOW ME THE FULL GPS ROUTE PLAN COMPLETE WITH LINKS TO THE WIKIPEDIA PAGES OF THE DISUSED RAILWAY LINES THAT COULD COME BACK INTO USE."
June 4, 2025 at 6:25 AM
What news editors and politicians think people want: "Just tell them they'll get a tram somewhere in their city if they're nice."
What people really want: "SHOW ME THE FULL GPS ROUTE PLAN COMPLETE WITH LINKS TO THE WIKIPEDIA PAGES OF THE DISUSED RAILWAY LINES THAT COULD COME BACK INTO USE."
What people really want: "SHOW ME THE FULL GPS ROUTE PLAN COMPLETE WITH LINKS TO THE WIKIPEDIA PAGES OF THE DISUSED RAILWAY LINES THAT COULD COME BACK INTO USE."
It's frustrating that this stuff isn't picked up by reviewers, and that the Exchange dataset is still being used when it's known to be a flawed benchmark. The fact this model beats the others is irrelevant, because all the models give bad results.
March 31, 2025 at 8:41 AM
It's frustrating that this stuff isn't picked up by reviewers, and that the Exchange dataset is still being used when it's known to be a flawed benchmark. The fact this model beats the others is irrelevant, because all the models give bad results.
It makes no sense of the uncertainty to be constant over the forecast horizon here (or in most time series models); the series is extremely unlikely to drop to half of its value in 1 time step, but this model suggests that has a ~5% chance of happening.
March 31, 2025 at 8:41 AM
It makes no sense of the uncertainty to be constant over the forecast horizon here (or in most time series models); the series is extremely unlikely to drop to half of its value in 1 time step, but this model suggests that has a ~5% chance of happening.