- Back to the Future of Handwriting Recognition -- a very readable explanation of how RAND's GRAIL system could read handwriting in 1966. (via Avi Bryant)
- The Surprising Security Benefits of End-to-End Formal Proofs -- talking up formal methods in software engineering, whereby you can prove your system's correctness.
- Software Foundations -- book series that is a broad introduction to the mathematical underpinnings of reliable software.
- Dank Learning: Generating Memes Using Deep Neural Networks -- both models generalize relatively well to unseen images. The average meme produced from both is difficult to differentiate from a real meme and both variants scored close to the same hilarity rating as real memes, though this is a fairly subjective metric. I wish "hilarity" were a metric that more things were judged by.
Article image: Four Short Links