Top all-time · #3718
Machined Learnings
Personal blog · machinedlearnings.comaidata
Machined Learnings is a personal blog at machinedlearnings.com about ai and data. Since 2010, 21 different Hacker News readers have linked it 22 times, most often “Software Engineering vs. Machine Learning Concepts”. The last post was in 2022, but the archive is still widely read.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
HN readers link this blog for posts on fast approximate math functions (log2, atan2), LDA implementations, and conference paper reviews. The comments cite or link the posts as sources and do not judge the writing.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
$\lim_{t \to \infty} V(s_t) \to 0$ so live accordingly
Most-linked posts?
- Software Engineering vs. Machine Learning Concepts2 people · 2 mentions · first linked 2017-02-16
What Hacker News says?
I actually think Machine Learning is relatively easy. There are a lot of resources, the community is very open, state-of-the-art tools are available, and all it needs to get incrementally better is trying out more stuff on different data sets. I worked in SEO before, which had far more elements of "black magic". Perhaps SEO helps with the transition to ML, because you are basically reverse engineering a model (Googl…
Comment linking /2013/06/productivity-is-about-not-waiting.html
on “Why is machine learning ‘hard’?”Submitted Stranger in a Strange Land: “Big Data” programmer meets HPC community as a story · 108 points
HN discussionRelated -- there's a 2011 post from Paul Minero with fast approximations for logarithm, exponential, power, inverse root. http://www.machinedlearnings.com/2011/06/fast-approximate-lo... Minero's faster approximate log2, < 1.4% relative error for x in [1/100, 10]. Here's the simple non-sse version: static inline float fasterlog2 (float x) { union { float f; uint32_t i; } vx = { x }; float y = vx.i; y *= 1.19209289550…
Comment linking /2011/06/fast-approximate-logarithm-exponential.html
on “Speeding up atan2f”Submitted Machined Learnings: LDA on a Social Graph as a story · 17 points
HN discussionVowpal Wabbit (one of the fastest learning implementations, from John Langford, also of Yahoo!) now has an "online" LDA implementation (Hoffman et al 2010: http://www.cs.princeton.edu/~blei/papers/HoffmanBleiBach2010... ). It's probably the fastest single-core LDA implementation. http://hunch.net/?p=1594 http://www.machinedlearnings.com/2010/12/lightning-fast-lda....
Comment linking /2010/12/lightning-fast-lda.html
on “Yahoo's hadoop-based Latent Dirichlet Allocation On Github”Submitted Software Engineering vs. Machine Learning Concepts as a story · 4 points
HN discussionAnother review which covers some different papers: http://www.machinedlearnings.com/2015/05/iclr-2015-review.ht...
Comment linking /2015/05/iclr-2015-review.html
on “ICLR 2015”Submitted Reinforcement Learning as a Service as a story · 3 points
HN discussionSubmitted Software Engineering vs. Machine Learning Concepts as a story · 3 points
HN discussionSubmitted Machined Learnings: ICML 2013: Sparse, Deep, and Random as a story · 3 points
HN discussionSubmitted Do you really have big data? as a story · 3 points
HN discussionSubmitted Is AI contributing to the inequality in America? as a story · 3 points
HN discussionSubmitted Machine Learning Blog as a story · 3 points
HN discussionSubmitted NIPS 2016 Reflections as a story · 2 points
HN discussionSubmitted NIPS 2012 Trends as a story · 2 points
HN discussionSubmitted How to Best a Human with a Spreadsheet as a story · 2 points
HN discussionSubmitted Xtranormal Bears talking about Machine Learning and Immigration Policy as a story · 2 points
HN discussionSubmitted Adversarial Scenarios and Economies of Scale as a story · 1 points
HN discussionSubmitted Killer screenshot at NIPS'14: get your own 1TB ram server as a story · 1 points
HN discussionSubmitted The Most Causal Observer as a story · 1 points
HN discussionSubmitted ML : Using less data as a story · 1 points
HN discussionSubmitted One louder: replacing regression with neural networks as a story · 1 points
HN discussion
