Top all-time · #17968
Jacob Gildenblat
Personal blog · jacobgil.github.ioaiprogramming
Jacob Gildenblat's personal blog at jacobgil.github.io covers ai and programming. Since 2017, 4 different Hacker News readers have linked it 6 times, most often “Overview of Active Learning for Deep Learning”. It is still writing: the last post was on 2026-08-30, and you can follow it by feed.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN commenters link this blog's posts on class activation maps, which show which parts of an image a neural network relies on for its label. One commenter calls one post the best introduction they found.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
👋 Welcome to my personal tech blog about Deep Learning, Machine Learning and Computer Vision. Since 2014.
Most-linked posts?
- /deeplearning/class-activation-maps2 people · 2 mentions · first linked 2019-04-14
- Overview of Active Learning for Deep Learning2 people · 2 mentions · first linked 2020-02-21
What Hacker News says?
https://jacobgil.github.io/deeplearning/class-activation-map... Not sure how that would work with a segmentation algorithm like Unet though. It makes more sense in showing where in an image that the network was activated to give the image a label. AFAIK Unet gives ever pixel a label so I don't see how you could do what the parent describes.
Comment linking /deeplearning/class-activation-maps
on “Distilling knowledge from neural networks to build smaller and faster models”Submitted Overview of Active Learning for Deep Learning as a story · 6 points
HN discussion"class activation map" is a new term to me, so I looked it up very briefly. Does it mean simply "what part of the image (or in aggregate, images) carried the strongest signal for categorization"? Or can it also tell you something about the feature set? Would you suggest and good introductory example to the concept? This was the best I found in my search https://jacobgil.github.io/deeplearning/class-activation-map...
Comment linking /deeplearning/class-activation-maps
on “The infamous “AI gaydar” study was repeated – couln't be reproduced”Submitted Overview of Active Learning for Deep Learning as a story · 5 points
HN discussionSubmitted Pruning deep neural networks to make them fast and small as a story · 3 points
HN discussionSubmitted Hallucinating faces with Dlib's face detector model in PyTorch as a story · 1 points
HN discussion