Top all-time · #631
MachineLearningMastery.com
Company blog · machinelearningmastery.comaiprogrammingdata
MachineLearningMastery.com is the company blog at machinelearningmastery.com, writing about ai, programming and data. Since 2013, 100 different Hacker News readers have linked it 167 times, most often “A Tour of Machine Learning Algorithms”. It is still writing: the last post was on 2026-11-02, and you can follow it by feed.
Sometimes recommended · 6 of 38 sampled comments recommend it?
Why HN links it
HN readers link Machine Learning Mastery for code-first tutorials on machine learning and time series, and for its books on Python statistics and linear algebra. Most links are bare citations.
Summarised by Claude from a sample of 38 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Making developers awesome at machine learning.
Most-linked posts?
- /5 people · 5 mentions · first linked 2016-05-12
- A Tour of Machine Learning Algorithms4 people · 4 mentions · first linked 2014-05-08
- Discover Feature Engineering, How to Engineer Features and How to Get Good at It3 people · 3 mentions · first linked 2014-09-25
- Your First Machine Learning Project in Python Step-By-Step3 people · 3 mentions · first linked 2019-01-29
- The Roadmap to Mastering Tool Calling in AI Agents2 people · 2 mentions · first linked 2026-05-07
- Mastering LLM Inference Optimization2 people · 2 mentions · first linked 2026-09-21
- Learn Vectorized Thinking in Python Through Examples2 people · 2 mentions · first linked 2026-08-26
- Text Generation with LSTM NNs in Python with Keras2 people · 2 mentions · first linked 2017-05-25
- Why Machine Learning Does Not Have to Be So Hard2 people · 2 mentions · first linked 2018-04-03
- Pretrain a Bert Model from Scratch2 people · 2 mentions · first linked 2025-11-28
What Hacker News says?
You're absolutely on the right track. There are well-established statistics tools that formalize your intuition and carry it forward to its logical conclusion. > "by day of week" This means you have a time series with daily resolution (one observation per day) and you expect Weekly Seasonality to matter. Model this as 7-period lag in your daily series. > based on % of increase from other markets if no previous years…
Comment linking /arima-for-time-series-forecasting-with-python/
on “You probably don't need AI/ML. You can make do with well written SQL scripts”Submitted A Gentle Introduction to Bayes’ Theorem for Machine Learning as a story · 305 points
HN discussionContrary to the other advice around here, I would strongly advise NOT taking a course. I think it is a good idea at some point, but it is not the first thing you should be doing. The very first thing you should do is play! Identify a dataset you are interested in and get the entire machine learning pipeline up and running for it. Here's how I would go about it. 1) Get Jupyter up and running. You don't really need to…
Comment linking /
on “Ask HN: How to get started with machine learning?”Submitted A Tour of Machine Learning Algorithms as a story · 207 points
HN discussionI think that this is a horribly impractical advice, and I keep seeing it everywhere. With modern tools and frameworks you can start learning and applying what you know on practice almost immediately. Check out Keras and the book "Deep Learning with Python"[1]. They have enabled me to train my first ANN in 2 days, and get to the point of building a MNIST recognizer in a month(and I was reading it pretty slowly). Sure…
Comment linking /deep-learning-with-python/
on “Ask HN: How to get started with machine learning?”Submitted Mistakes Programmers Make when Starting in Machine Learning as a story · 128 points
HN discussionUnlike the other subjects contained in this book, I do not think that any useful understanding of Probability and Statistics could result from only one or two chapters of coverage. I would recommend a book I found that covers Statistics using Python: Statistical Methods for Machine Learning https://machinelearningmastery.com/products/ Personally, I much prefer that book to the free "Think Stats" one available. You c…
Comment linking /products/
on “A Programmer's Introduction to Mathematics”Submitted Applied Machine Learning Is a Meritocracy as a story · 127 points
HN discussionI liked this. It’s a different approach so take a look at the free pages. Not for everyone but worth a look to see if it fits you. Bonus: the author is responsive. https://machinelearningmastery.com/linear_algebra_for_machin...
Comment linking /linear_algebra_for_machine_learning/
on “Calculus Made Easy (1910)”Submitted Logistic Regression for Image Classification Using OpenCV as a story · 81 points
HN discussion? I've always thought that ML/AI for me was about learning the languages that could express my idea of how it could work. In order to do that myself, I started reading about algorithm types. http://machinelearningmastery.com/a-tour-of-machine-learning... There was one particular study piece that I remember reading that I believe was written in the late 70's early 80's, but I can't remember its name. It was a HTML un…
Comment linking /a-tour-of-machine-learning-algorithms/
on “Ask HN: What free resources did you use to learn how to program ML/AI?”Submitted A Tour of Machine Learning Algorithms as a story · 68 points
HN discussionIn OP [1]. [1] https://machinelearningmastery.com/deep-learning-for-time-se...
Comment linking /deep-learning-for-time-series-forecasting/
on “Time Series Prediction – A short introduction for pragmatists”Submitted Clustering Algorithms with Python as a story · 54 points
HN discussionI'm not an expert, but the best one I could find is this: https://machinelearningmastery.com/deep-learning-with-python... Really neat intro, simple examples, using high level libraries (Keras and TF).
Comment linking /deep-learning-with-python/
on “Google Releases Colaboratory”Submitted A Gentle Introduction to Serialization for Python as a story · 33 points
HN discussion> these work best on predictable things Umm, not really. You are talking about single and multi-label classification tasks, maybe? Bengali poetry is just like poetry in any other rich languages like English, French, etc. What these models do, from a high level, is that they learn the distribution of the data. In this case, they learn the style of the poets. Writing poetry in specific styles has been done long before…
Comment linking /text-generation-lstm-recurrent-neural-networks-python-keras/
on “GPT-3 is no longer the only game in town”Submitted How and When to Use ROC Curves and Precision-Recall Curves for Classification as a story · 29 points
HN discussionYes. An Introduction to Statistical Learning https://github.com/tpn/pdfs/blob/master/An%20Introduction%20... Deep Learning https://books.google.com/books/about/Deep_Learning.html?id=o... Machine Learning Mastery books https://machinelearningmastery.com/products/ Convolutional Neural Networks from the Ground Up https://towardsdatascience.com/convolutional-neural-networks... Transformers https://medium.com/inside-mach…
Comment linking /products/
on “New Fast.ai Course: A Code-First Introduction to Natural Language Processing”Submitted Deep Learning Books as a story · 18 points
HN discussionMachine Learning Mastery ( https://machinelearningmastery.com ) provides code examples for many of the popular models. For me, seeing and writing code has been helpful in understanding how things work and makes it easier to put new developments in context.
Comment linking /
on “Ask HN: Recommendation for a SWE looking to get up to speed with latest on AI”Submitted Pretrain a Bert Model from Scratch as a story · 9 points
HN discussionSo, there's a lot of material out there but it's disjointed. If you get annoyed implementing your own neural net with only Python + Numpy, you might try some more complex examples just to immediately point at them and say "I ran this" and "It did that". (The article uses neural networks so I'm addressing that here even though your question and the article title use the much broader 'ML'.) 1) Brandon Rohrer, now Data…
Comment linking /
on “MNIST for ML Beginners: The Bayesian Way”Submitted A Tour of Recurrent Neural Network Algorithms for Deep Learning (2017) as a story · 6 points
HN discussion> How good will your deep fake have to be in order to fool a deep fake detection AI? The best generator and the best detector are actually part of the same model! If you create a better detector, you are making the generator better at the same time so you have not accomplished anything. "GANs are a clever way of training a generative model by framing the problem as a supervised learning problem with two sub-models:…
Comment linking /what-are-generative-adversarial-networks-gans/
on “Creating a deepfake took two weeks and cost $552”Submitted The Seductive Trap of Black-Box Machine Learning as a story · 6 points
HN discussionThat's called 'data leakage'. http://machinelearningmastery.com/data-leakage-machine-learn...
Comment linking /data-leakage-machine-learning/
on “Thoughts on OpenAI, reinforcement learning, and killer robots”Submitted A Gentle Introduction to Information Entropy as a story · 5 points
HN discussion> You’re not going to teach your dog relativity with back propagation What do you mean? RNN's can be taught to do math using BP[1]. Heck, you can do a simple version yourself in less than an hour[2]. They can't do tensor calculus yet (AFAIK) but there doesn't seem be any reason why BP in particular would be the stumbling block; the difficulty is finding the right representation. > yet we treat BP like it was going t…
Comment linking /learn-add-numbers-seq2seq-recurrent-neural-networks/
on “Theories of Error Back-Propagation in the Brain”Submitted A Gentle Introduction to Bayesian Belief Networks as a story · 5 points
HN discussion
