Top all-time · #10907
Machine Learning, etc
Personal blog · yaroslavvb.blogspot.com · on HN as yaroslavvbaidata
Machine Learning, etc is a personal blog at yaroslavvb.blogspot.com about ai and data. Since 2009, 7 different Hacker News readers have linked it 8 times, most often “How to Patent an Algorithm”. The last post was in 2017, but the archive is still widely read.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN readers link this blog for its notMNIST dataset post, which one commenter cites as a harder alternative to MNIST. The comments cite it as a resource rather than evaluating the writing.
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.
Most-linked posts?
- How to Patent an Algorithm2 people · 2 mentions · first linked 2011-02-22
What Hacker News says?
Actually, I ran into a relevant discussion on the topic with a few choice quotes (from [1]): When filing an algorithm patent, patent lawyer will tell you to remove every instance of the word "algorithm" and replace it with some other word. This seems to be necessary for getting the patent through. [...] at some point you may find yourself pulling diagrams from thin air and thinking "why am I doing this?" (but then r…
Comment linking /2011/02/how-to-patent-algorithm-in-us.html
on “Damn Cool Algorithms: Fountain Codes”Submitted Neural Networks making a come-back? as a story · 64 points
HN discussionFor a MNIST-like dataset, I often use not-MNIST ( http://yaroslavvb.blogspot.com/2011/09/notmnist-dataset.html ), which is more difficult than the original one (see examples of misclassified digits here: https://docs.neptune.ml/get-started/character-recognition/ ). However, I am not sure if we need more MNIST-like datasets. With small size many things make much less sense (data augmentation, even convnets as images…
Comment linking /2011/09/notmnist-dataset.html
on “An MNIST-like fashion product dataset”Submitted Machine Learning opportunities at Google as a story · 5 points
HN discussionBTW, tree decomposition is a generalization of dynamic programming. In a general structured problem you may not have a nice table recursion like in edit-distance example, and tree decomposition is what you get when you abstract away from tables. When problem structure comes from the real world, like with probabilistic networks, computers are much better at finding a good recursion than humans. Here are some pictures…
Comment linking /2011/02/generalized-distributive-law.html
on “Visualizing dynamic programming”Submitted Visualizing 7 dimensional simplex as a story · 4 points
HN discussionI was in your boat several months ago when I had to learn image processing from scratch to implement a requested feature "Digital Image Processing Using MATLAB" ended up the most useful, along with some basic Matlab tutorials here's what I ended up with http://yaroslavvb.blogspot.com/2009/08/robust-ocr-in-video.h...
Comment linking /2009/08/robust-ocr-in-video.html
on “Ask HN: Image recognition books and resources”Submitted How to Patent an Algorithm as a story · 2 points
HN discussion
