1651
A Visual Exploration of Gaussian Processes
Consulting software engineer and research scientist. I build visualization systems for complex data and machine learning models.
New
The latest blog posts to take off on Hacker News. 2,851 posts.
1652
Pathfinding for Tower Defense
In a Tower Defense game, there are many enemies that are all headed to the same place. In many Tower Defense games, there is a predetermined path, or a small number of paths. In some, such as the classic Desktop Tower Defense [1] , you can place towers anywhere, and they act as obstacles that affect the paths taken by…
1653
Understanding is a poor substitute for convexity (2012)
Something central, very central, is missing in historical accounts of scientific and technological discovery. The discourse and controversies focus on the role of luck as opposed to teleological programs (from telos, "aim"), that is, ones that rely on pre-set direction from formal science. This is a faux-debate: luck…
1654
How long is that Bézier?
Blog of Raph Levien.
1655
Connected Components – The one Graph Algorithm you need to know
Graphs provide us with a very useful data structure.
1656
Deciphering the postcard-sized raytracer
"He's done it again!" was my first thought as I looked at the back of a postcard sized Pixar flier [1] which was covered in code. In the lower right corner, the blob of statements and expressions had been signed by none other than Andrew Kensler. For those who are not familiar with him, Andrew is the programmer who…
1657
The Wavefunction Collapse Algorithm Explained
The Wavefunction Collapse Algorithm teaches your computer how to riff. The algorithm takes in an archetypical input, and produces procedurally-generated outputs that look like it.
1658
Why are amplitudes complex?
[By prior agreement, this post will be cross-posted on Microsoft’s Q# blog, even though it has nothing to do with the Q# programming language. It does, however, contain many examples th…
1659
Advent of Code Python Solutions, Explained
I first participated in Advent of Code (AoC) in 2017. My co-workers at Formlabs introduced it to me. This year (2018), quite a lot of Formlabs folks are taking part and we have a nice private leaderboard going. I'm having a lot of fun with it. I've been staying up until midnight to work on the problems as soon as…
1660
Neural Networks as Ordinary Differential Equations
Recently I found a paper being presented at NeurIPS this year, entitled Neural Ordinary Differential Equations, written by Ricky Chen, Yulia Rubanova, Jesse Bettencourt, and David Duvenaud from the University of Toronto. The core idea is that certain types of neural networks are analogous to a discretized differential…
1661
How AI Training Scales
Stay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
1662
Machine Learning Trick of the Day: Instrumental Thinking
· Read in · 1499 words · All posts in series · [dropcap]This[/dropcap] trick is unlike the others we’ve conjured. It will not reveal a clever manipulation of a probability or an integral or a…
1663
1664
Secrets of smooth Béziers
I haven’t posted here much lately, and I admit, it’s because I’ve gotten sidetracked thinking about curves again. I did my PhD thesis on curves, so spent years thinking about them, then put that on hold for a while, aside from some work in crunching font file sizes down.
1665
1666
Hamiltonian Monte Carlo explained
Understanding an effective way of sampling from complex distributions with 3d-demonstrations
1667
Algebras we love
If you work with anything that can be modeled mathematically, you most likely know that many things you work on can be expressed with algebras. However, if you are not a graduate of a computer science course or similar you might not know how ubiquitous they are and how often you rely on some of them. (And I don’t mean…
1668
A Programmer's Introduction to Mathematics
For the last four years I’ve been working on a book for programmers who want to learn mathematics. It’s finally done, and you can buy it today. The website for the book is pimbook.org, which has purchase links—paperback and ebook—and a preview of the first pages. You can see more snippets later in the book on the…
1669
The deepest problem with deep learning
Some reflections on an accidental Twitterstorm, the future of AI and deep learning, and what happens when you confuse a schoolbus with a…
1670
How to design co-programs
I recently attended the Matthias Felleisen Half-Time Show, a symposium held in Boston on 3rd November in celebration of Matthias’s 60th birthday. I was honoured to be able to give a talk ther…
1671
Math and Analogies
Here's a talk on "Math And Analogies" I did for the Center on Contemporary Art (CoCA) in Seattle. What's this? Well, it's a number. Probably written down a…
1672
Ryanair, Hamiltonian Cycles, and using graph theory to find cheap flights
Using graph theory and Ryanair route data to find cheap multi-city flight loops through Europe.
1673
1674
Fast, Constant-Time Sphere Indexing
Map any 3D point on or above a triangle-subdivided sphere to a triangle index in constant time, without recursion, table lookups or complicated branching logic.
1675
Shamir’s Secret Sharing Scheme
Consider a scenario in which you are tasked with managing the security of a bank's vault. The vault is considered impenetrable without a key, which you are g...
1676
Kelly Criterion (2007)
It’s fairly clear when one should buy a particular stock. One should buy stock when it is undervalued. What I have always wondered about is how much stock one should buy. A few months ago I stumbled upon the answer which is given by the Kelly criterion . It says that one should invest an amount to maximize one’s…
1677
Estimating the chances of something that hasn’t happened yet
A handy rule of thumb for creating a confidence interval for the probability of an event you haven't seen happen yet.
1678
Learning Concepts with Energy Functions
Stay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
1679
1680
Getting started with linear algebra
I'd like to introduce a series of blog posts and their corresponding Python Notebooks gathering notes on the Deep Learning Book from Ian Goodfellow, Yoshua B...