Tutorials on the scientific Python ecosystem: a quick introduction to central tools and techniques. The different chapters each correspond to a 1 to 2 hours course with increasing level of expertise, from beginner to expert.
A great intro to Scipy and the things your can do with it.
There’s something magical about Recurrent Neural Networks (RNNs). I still remember when I trained my first recurrent network for Image Captioning. Within a few dozen minutes of training my first baby model (with rather arbitrarily-chosen hyperparameters) started to generate very nice looking descriptions of images that were on the edge of making sense. Sometimes the ratio of how simple your model is to the quality of the results you get out of it blows past your expectations, and this was one of those times. What made this result so shocking at the time was that the common wisdom was that RNNs were supposed to be difficult to train (with more experience I’ve in fact reached the opposite conclusion). Fast forward about a year: I’m training RNNs all the time and I’ve witnessed their power and robustness many times, and yet their magical outputs still find ways of amusing me. This post is about sharing some of that magic with you.
The best tutorial I’ve read on NLP-friendly RNNs.
Over the last 13 months, at least three top-tier corporate clients have walked away, including Coca-Cola, American Express, and Nasdaq, according to internal documents. Palantir mines data to help companies make more money, but clients have balked at its high prices that can exceed $1 million per month, expressed doubts that its software can produce valuable insights over time, and even experienced difficult working relationships with Palantir’s young engineers. Palantir insiders have bemoaned the “low-vision” clients who decide to take their business elsewhere.
A bit off topic, but I’m becoming increasingly impressed with BuzzFeed’s journalistic output.