Top all-time · #3596
i am trask
Personal blog · iamtrask.github.ioaiprogramming
i am trask is a personal blog at iamtrask.github.io about ai and programming. Since 2014, 21 different Hacker News readers have linked it 54 times, most often “A Neural Network in 11 Lines of Python”. It is still writing: the last post was on 2026-04-07, and you can follow it by feed.
Too few sampled comments (15) to say how often HN recommends it.?
Why HN links it
HN readers link this blog for short, from-scratch neural network examples in Python, especially the 11-line network post, and as a source for learning deep learning.
Summarised by Claude from a sample of 15 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
A machine learning craftsmanship blog.
Most-linked posts?
- A Neural Network in 11 Lines of Python7 people · 7 mentions · first linked 2016-03-28
- A Neural Network in 11 Lines of Python (2015)5 people · 7 mentions · first linked 2015-07-14
- How to Code and Understand DeepMind's Neural Stack Machine2 people · 2 mentions · first linked 2016-03-28
- I am Trask: machine learning craftsmanship blog2 people · 2 mentions · first linked 2017-10-13
- A neural network in 13 lines of python (Part 2 - Stochastic Gradient Descent)2 people · 2 mentions · first linked 2015-07-28
- Grokking Deep Learning2 people · 2 mentions · first linked 2016-08-18
What Hacker News says?
The visualization is cool, thanks! Here's another neural network example from scratch in 13 lines of Python: https://iamtrask.github.io/2015/07/27/python-network-part2/
Comment linking /2015/07/27/python-network-part2/
on “Implementing a Neural Network from Scratch in Python”Submitted Grokking Deep Learning as a story · 530 points
HN discussionAn alternate theory is that you can make use of ML to do useful tasks through an understanding of just high school math (basic algebra) and basics of python. I'm not sure if that's actually true, but I'm inclined to be in this camp as abstractions are used in virtually every other tasks. The amount of extra value that can be had from applying even basic ML techniques is so great, that there is probably a lot of upsi…
Comment linking /2016/08/17/grokking-deep-learning/
on “Learning Machine Learning: A beginner's journey”Submitted A Neural Network in 11 Lines of Python as a story · 341 points
HN discussionThey are, but once you start learning about them, you realize the "black magic" part comes mostly from their mathematical nature and very little from them being "inteligent computers". A neural net is a graph, in which a subset of nodes are "inputs" (that's where the net gets information), some are outputs, and there are other nodes which are called "hidden neurons". The nodes are interconnected between each other i…
Comment linking /2015/07/12/basic-python-network/
on “How Google Translate squeezes deep learning onto a phone”Submitted A Neural Network in 11 Lines of Python (2015) as a story · 234 points
HN discussionI'm also starting to follow people and communities that work with deep learning in new ways. Here are some of my favorites: [1] http://colah.github.io/ [2] https://iamtrask.github.io/ [3] https://distill.pub [4] https://experiments.withgoogle.com/ai
Comment linking /
on “Colorizing black and white photos with deep learning”Submitted Building Safe AI: A Tutorial on Homomorphically Encrypted Deep Learning as a story · 228 points
HN discussionYes for sure. I am very math-averse (almost failed calculus 1, skated by pre-calc in high school... not my intelligence area) and though I don't have a full time job doing something in AI, I do feel like I can build models that solve real problems (and am doing so in an internship right now). Probably start with Andrew Ng's Machine Learning course. It has a significant amount of Math in it-- try to understand it, bu…
Comment linking /2015/07/12/basic-python-network/
on “Thoughts on OpenAI, reinforcement learning, and killer robots”Submitted How to Code and Understand DeepMind's Neural Stack Machine in Python as a story · 198 points
HN discussionI 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 /2015/07/12/basic-python-network/
on “A friendly Introduction to Backpropagation in Python”Submitted Deep Learning without Backpropagation as a story · 133 points
HN discussionIf people like "give me the simplest possible working coding example" of neural networks, I highly recommend this one: "A Neural Network in 11 lines of Python (Part 1)": https://iamtrask.github.io/2015/07/12/basic-python-network/
Comment linking /2015/07/12/basic-python-network/
on “Towards the Cutest Neural Network”Submitted Anyone Can Learn to Code an LSTM-RNN (Part 1: RNN) as a story · 125 points
HN discussionby the way, it is a ports from 11 lines python version here: http://iamtrask.github.io/2015/07/12/basic-python-network/ , isn't it more readable concise and beautiful than python version? if our all ML codes use apl, it will be a cool world.
Comment linking /2015/07/12/basic-python-network/
on “APL in R”Submitted Deep Learning with PyTorch – An Unofficial Startup Guide as a story · 84 points
HN discussionPer your last comment, I'm thinking about changing this blog series to be a "blog" version of academic papers... starting with this one. https://iamtrask.github.io/2016/02/25/deepminds-neural-stack...
Comment linking /2016/02/25/deepminds-neural-stack-machine/
on “A Neural Network in 11 Lines of Python”Submitted A Neural Network in 11 Lines of Python as a story · 82 points
HN discussionThat reminds me of the article „a neural network in 11 lines of code“ from 2015 (although not on MNIST, rather some kind of XOR) https://iamtrask.github.io/2015/07/12/basic-python-network/
Comment linking /2015/07/12/basic-python-network/
on “Ultra simplified "MNIST" in 60 lines of Python with NumPy”Submitted Safe Crime Prediction: Encrypted Deep Learning for Less Intrusive Surveillance as a story · 49 points
HN discussionThis is a very poor article. It manages to both be demeaning to people who want to learn something new while also being riddled with factual errors. Here are just a few factual errors: 1. The 11-line example is the simplest possible neural network with a very basic implementation of gradient descent in a high-level vectorization framework (numpy). It's exactly what you'd cover in the first week of a course on neural…
Comment linking /2015/07/12/basic-python-network/
on “Neural network AI is simple. So… Stop pretending you are a genius”Submitted Distributing a Fully Connected Neural Network Across a Cluster as a story · 30 points
HN discussionFor interesting reads in Deep learning I follow these: - https://distill.pub/ - http://colah.github.io/ - https://lexfridman.com/ai/ - http://iamtrask.github.io/ And some interesting reads on Uncertainty in Deep Learning http://mlg.eng.cam.ac.uk/yarin/blog_2248.html
Comment linking /
on “Ask HN: Who to Follow on the Internet in 2020?”Submitted A bare bones neural network in Python to teach backpropagation (2015) as a story · 22 points
HN discussionThe below resources are the ones I used when I started to learn about DL/NNs. Some of them are focused specifically on certain applications, but I found them helpful, too. Basic NNs: http://www.wildml.com/2015/09/implementing-a-neural-network-... (a whole series, all worth reading) https://gist.github.com/sthware/c47824c116e6a61a56d9 (my code based on the above) http://iamtrask.github.io/2015/07/27/python-network-pa…
Comment linking /2015/07/27/python-network-part2/
on “Ask HN: Where to begin learning about Neural Nets”Submitted A neural network in 13 lines of python (Part 2 - Stochastic Gradient Descent) as a story · 17 points
HN discussionThe original Python implemation found at: http://iamtrask.github.io/2015/07/12/basic-python-network/ X =: 4 3 $ 0 0 1 0 1 1 1 0 1 1 1 1 Y =: 4 1 $ 0 0 1 1 w =: 3 1 $ 0.5069797399 0.5703818579 0.9265880619 e =: 2.718281828459045 iter =: ^: dot =: +/ . * T =: |: output =: verb define 1 % 1 + e ^ 0 - X dot y ) train =: verb define l1 =: output y l1_err =: Y - l1 l1_delta =: l1_err * l1 * 1 - l1 y + (T X) dot l1_delta )…
Comment linking /2015/07/12/basic-python-network/
on “Simple Neural Network in 22 lines J lang without library”Submitted Tutorial: when Numpy isn't fast enough... as a story · 15 points
HN discussionDid you forget the link? :) http://iamtrask.github.io/2015/07/12/basic-python-network/
Comment linking /2015/07/12/basic-python-network/
on “A Neural Network in 11 Lines of Python (Pt.1)”Submitted Tutorial: Apache Spark on GPU(s) as a story · 12 points
HN discussion
