/explore
|
You are here 
|
research.google | ||
| | | | |
blog.research.google
[AI summary] Google Research presents a lightweight algorithm called Stochastic Re-weighted Gradient Descent (RGD) that improves deep learning model performance by automatically weighting data points based on their difficulty within a distributionally robust optimization framework. |
|
| | | | | ||
| | | | |
tech.preferred.jp
This post is a contribution by Zongyao Li, who was an intern at PFN. I am Zongyao Li, a Ph. D. student at Graduate School of Information Science of Technology, Hokkaido University. I participated in the PFN summer internship program in 2022. During the internship, I did research on test-time adaptation for brain tumor segmentation with cross-institutional MRI. In this article, I would like to share our ideas and results in the research. |
|
| | | | | ||
| | | | |
anitagraser.com
It's been a while since my post on geo and the AI hype in 2019. Back then, I didn't use the term "GeoAI", even though it has certainly been around for a while (including, e.g., with dedicated SIGSPATIAL workshops since 2017). GeoAI isn't one single thing. It's an umbrella term, including: "AI for Geo" (using... |
|
| | | | | ||
| | | | |
wtfleming.github.io
[AI summary] This post discusses achieving 99.1% accuracy in binary image classification of cats and dogs using an ensemble of ResNet models with PyTorch. |
|
| | | |||
