Overviews of Graph Classification and Network Clustering methods

Thanks to Sebastian Raschka I am able to share this great GitHub overview page of relevant graph classification techniques, and the scientific papers behind them. The overview divides the algorithms into four groups: Factorization Spectral and Statistical Fingerprints Deep Learning Graph Kernels Moreover, the overview contains links to similar collections on community detection, classification/regression trees and gradient boosting papers…

ArchiGAN: Designing buildings with reinforcement learning

I’ve seen some uses of reinforcement learning and generative algorithms for architectural purposes already, like these evolving blueprints for school floorplans. However, this new application called ArchiGAN blew me away! ArchiGAN (try here) was made by Stanislas Chaillou as a Harvard master’s thesis project. The program functions in three steps: building footprint massing program repartition…

3D visual representations of common neural network architectures

Came across this awesome Youtube video that blew my mind. Definitely a handy resource if you want to explain the inner workings of neural networks. Have a look! Reminded me of my other go-to resource when it comes to explaining neural nets, the playlists by 3Blue1Brown: I’ll surely add these to the other neural network…

Artificial Stupidity – by Vincent Warmerdam @PyData 2019 London

PyData is famous for it’s great talks on machine learning topics. This 2019 London edition, Vincent Warmerdam again managed to give a super inspiring presentation. This year he covers what he dubs Artificial Stupidity™. You should definitely watch the talk, which includes some great visual aids, but here are my main takeaways: Vincent speaks of…

Free Programming Books (I still need to read)

There are multiple unread e-mails in my inbox. Links to books. Just sitting there. Waiting to be opened, read. For months already. The sender, you ask? Me. Paul van der Laken. A nuisance that guy, I tell you. He keeps sending me reminders, of stuff to do, books to read. Books he’s sure a more…

Awful AI: A curated list of scary usages of artificial intelligence

I found this amazingly horrifying list called Awful Artificial Intelligence: Artificial intelligence [AI] in its current state is unfair, easily susceptible to attacks and notoriously difficult to control. Nevertheless, more and more concerning the uses of AI technology are appearing in the wild. [Awful A.I.] aims to track all of them. We hope that Awful AI can be a platform to spur…

Beating Battleships with Algorithms and AI

Past days, I discovered this series of blogs on how to win the classic game of Battleships (gameplay explanation) using different algorithmic approaches. I thought they might amuse you as well : ) The story starts with this 2012 Datagenetics blog where Nick Berry constrasts four algorithms’ performance in the game of Battleships. The resulting levels…

Tensorflow for R Gallery

Tensorflow is a open-source machine learning (ML) framework. It’s primarily used to build neural networks, and thus very often used to conduct so-called deep learning through multi-layered neural nets.  Although there are other ML frameworks — such as Caffe or Torch — Tensorflow is particularly famous because it was developed by researchers of Google’s Brain…

Dragonflies and neural networks

Did you know that dragonflies are one of the most effective and accurate predators alive? And that while it has a brain consisting of very few neurons. Neuroscientist Greg Gage and his colleagues studied how a dragonfly locks onto its preys and captures it within milliseconds. Actually, a dragonfly seems to be little more than…