Computer Vision: Why It Matters and Which Libraries to Learn
A practical introduction to computer vision, its main tasks, and the Python libraries worth learning for real projects.
Writing · Notes and essays
RSSWorking thoughts across AI/ML, engineering, physics, the universe, and the future of civilization.
07 published notes across 06 topics.
Intelligent systems, models, evaluation, and the questions behind them.
1 post02Images, perception, medical imaging, segmentation, and visual learning.
1 post03Full-stack systems, architecture, implementation, and lessons from building.
0 posts04Machine learning, deep learning, experiments, papers, and practical intuition.
2 posts05Astronomy, cosmology, scale, time, and our place in the universe.
1 post06Curiosity, learning, research life, uncertainty, and ideas still taking shape.
2 postsA practical introduction to computer vision, its main tasks, and the Python libraries worth learning for real projects.
A simple thought about comparison, quiet progress, and the feeling that everyone else has already figured life out.
A structured guide to the main ML and DL concepts, from data and evaluation to neural networks, transformers, and deployment.
How ML and deep learning turn multispectral satellite data into maps of land, water, crops, cities, disasters, and change.
We can look billions of years into the past, but the universe has hidden its first moments behind a wall no telescope can see through.
Moonshot AI's 2.8-trillion-parameter Kimi K3 is open-weight and multimodal. Here is what it offers—and the hardware needed to run it.
A place to think in public about intelligent systems, visual understanding, software, research, and the universe beyond all of them.