Tootfinder

I keep using "thinner iPad" as my main example for the lack of vision and innovativeness of the tech sector. Not sure "thinner iPhone" hits as hard but I really love how Apple makes my case.

Tidy Modeling with R: #rstats #machinelearning

Tidy Modeling with R
The tidymodels framework is a collection of R packages for modeling and machine learning using tidyverse principles. This book provides a thorough introduction to how to use tidymodels, and an outline of good methodology and statistical practice for phases of the modeling process.

Microsoft Research, Providence, and UW develop the GigaTIME AI model, aiming to perform tumor analysis in a fraction of the time and cost of existing methods (Lisa Stiffler/GeekWire)
https://www.geekwire.com/2025/microsoft-an

🇺🇦 #NowPlaying on KEXP's #Early
Gorillaz:
🎵 Tomorrow Comes Today
#Gorillaz
https://psychosilence.bandcamp.com/album/gorillaz-tomorrow-comes-today-psycho-silence-bootleg
https://open.spotify.com/track/6BL4PpswVjH9BAajbIbpmZ

Not finished today, but surely surely finished tomorrow!?
Mirrors stuck onto the doors. Quite a lot of mirror. Makes the room feel bigger.
All the trim and handles are on now. Just one hole for cables missing. Catches need to be put on the blind-doors. Adjusting the doors so they open and close smoothly. Couple of lights to be attached. Painting and decorating touch-up.
Actually do believe they'll finish tomorrow.

🇺🇦 Auf radioeins läuft...
Oddisee:
🎵 Tomorrow Cant Be Borrowed
#NowPlaying #Oddisee
https://oddiseemmg.bandcamp.com/track/tomorrow-cant-be-borrowed
https://open.spotify.com/track/5M6SxlexdN7HrnjNrNrwAK

SER-Diff: Synthetic Error Replay Diffusion for Incremental Brain Tumor Segmentation
Sashank Makanaboyina
https://arxiv.org/abs/2510.06283 https://arxiv.org…

SER-Diff: Synthetic Error Replay Diffusion for Incremental Brain Tumor Segmentation
Incremental brain tumor segmentation is critical for models that must adapt to evolving clinical datasets without retraining on all prior data. However, catastrophic forgetting, where models lose previously acquired knowledge, remains a major obstacle. Recent incremental learning frameworks with knowledge distillation partially mitigate forgetting but rely heavily on generative replay or auxiliary storage. Meanwhile, diffusion models have proven effective for refining tumor segmentations, but h…

Announcing Prairie Voice: Where Yesterday’s Wisdom Meets Tomorrow’s Questions
Prairie Voice launches today, not because the world needs another website, but because the present has become incomprehensible without the past. We live in an age of unprecedented change, facing questions that feel entirely new: How do we maintain human connection through screens? What does work mean when we produce nothing tangible? How do we raise children when childhood itself has been…

Validation of Various Normalization Methods for Brain Tumor Segmentation: Can Federated Learning Overcome This Heterogeneity?
Jan Fiszer, Dominika Ciupek, Maciej Malawski
https://arxiv.org/abs/2510.07126

Validation of Various Normalization Methods for Brain Tumor Segmentation: Can Federated Learning Overcome This Heterogeneity?
Deep learning (DL) has been increasingly applied in medical imaging, however, it requires large amounts of data, which raises many challenges related to data privacy, storage, and transfer. Federated learning (FL) is a training paradigm that overcomes these issues, though its effectiveness may be reduced when dealing with non-independent and identically distributed (non-IID) data. This study simulates non-IID conditions by applying different MRI intensity normalization techniques to separate da…

🇺🇦 #NowPlaying on KEXP's #DriveTime
Wire:
🎵 Ex Lion Tamer
#Wire
https://thedownhouseca.bandcamp.com/track/ex-lion-tamer-wire-cover