Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #13648

P

Peter’s Notes

Personal blog · peterroelants.github.io/postsaimathprogramming

Peter’s Notes is a personal blog at peterroelants.github.io about ai, math and programming. Since 2015, 5 different Hacker News readers have linked it 13 times, most often “Gaussian Processes from Scratch (2019)”. It is still writing: the last post was on 2026-06-14, and you can follow it by feed.

Visit the blog
13mentions?
5HN people?
2015–2025first – last linked?
Links on Hacker News per year · peak 3 in 2018

Too few sampled comments (2) to say how often HN recommends it.?

Why HN links it

HN readers link Peter's Notes for its machine learning posts with code, such as Gaussian processes from scratch and a Python backpropagation introduction. One commenter also praises the site's design.

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.

Notes on machine learning, probability, mathematics, and software engineering, with visual explanations and from-scratch implementations.

Most-linked posts?

  1. Gaussian Processes from Scratch (2019)
    2 people · 2 mentions · first linked 2019-01-07

What Hacker News says?

  1. Just want to say, the website itself is totally gorgeous. Love how it looks on mobile, love the math rendering, looks awesome. (And thanks for making the code available too.) EDIT: Turns out, there’s more info here about how to set up a site like this: https://peterroelants.github.io/posts/about-this-blog/

    Comment linking /posts/about-this-blog/

    on “Gaussian Processes from Scratch (2019)”
  2. Submitted Gaussian Processes from Scratch (2019) as a story · 171 points

    HN discussion
  3. I had a really good time adapting Karpatny's blog post to python myself but it didn't give me sufficient understanding so i continued with [1], then [2] and finally deciphering [3]. [1] https://mattmazur.com/2015/03/17/a-step-by-step-backpropagat... [2] http://peterroelants.github.io/posts/neural_network_implemen... [3] https://iamtrask.github.io/2015/07/12/basic-python-network/

    Comment linking /posts/neural_network_implementation_part04/

    on “A friendly Introduction to Backpropagation in Python”
  4. Submitted Simple Python implementation of a Bayesian multi-armed bandit algorithm as a story · 117 points

    HN discussion
  5. This is a short series on Gaussian Processes I've been working on for a while. It's a 3 part series: 1. Part 1 introduces the concept of Gaussian processes with the help of a simple Python implementation: https://peterroelants.github.io/posts/gaussian-process-tutor... 2. Part 2 illustrates how to practically fit kernel hyperparameters to data with the help of TensorFlow probability: https://peterroelants.github.io/p…

    Comment linking /posts/gaussian-process-kernels/

    on “Understanding Gaussian Processes. Implementation and TF-Probability Example”
  6. Submitted How to implement a neural network: Part 1 as a story · 66 points

    HN discussion
  7. Submitted Flow Matching: A Visual Introduction as a story · 8 points

    HN discussion
  8. Submitted Understanding Gaussian Processes. Implementation and TF-Probability Example as a story · 4 points

    HN discussion
  9. Submitted ReAct REPL Agent: GPT with the ability to search and chain API calls as a story · 2 points

    HN discussion
  10. Submitted Linear regression implemented four different ways (MLE, OLS, GD, MCMC) as a story · 2 points

    HN discussion
  11. Submitted A short primer on the multivariate normal distribution as a story · 1 points

    HN discussion

Search all of HN for peterroelants.github.io