Web Picks (week of 3 October 2016)

Every two weeks, we find the most interesting data science links from around the web and collect them in Data Science Briefings, the DataMiningApps newsletter. Subscribe now for free if you want to be the first to get up to speed on interesting resources.

  • What is hardcore data science—in practice?
    The anatomy of an architecture to bring data science into production. Great article for anyone trying to understand the issues in bring data science from development to production.
  • The Fundamental Limits of Machine Learning
    “As a human, the challenge is to find any pattern at all. Of course, we have intuitions that limit our guesses. But computers have no such intuitions. From a computer’s standpoint, the difficulty in pattern recognition is one of surplus: with an endless variety of patterns, all technically valid, what makes one “right” and another “wrong?””
  • Generative Visual Manipulation on the Natural Image Manifold
    “Realistic image manipulation is challenging because it requires modifying the image appearance in a user-controlled way, while preserving the realism of the result. Unless the user has considerable artistic skill, it is easy to “fall off” the manifold of natural images while editing. In this paper, we propose to learn the natural image manifold directly from data using a generative adversarial neural network.”
  • traces – A Python library for unevenly-spaced time series analysis
    Taking measurements at irregular intervals is common, but most tools are primarily designed for evenly-spaced measurements. Also, in the real world, time series have missing observations or you may have multiple series with different frequencies: it’s can be useful to model these as unevenly-spaced.
  • Deep learning goes wide
    A company called Bonsai joins a movement to democratize machine learning. Get ready to build your own neural net.
  • AI generates abstract diagrams of IQ tests as good as 10th grade students
    Amazing work: “So, we can say that our model is very good generator and comparable to even 10th grade humans. An interesting aspect is that the model is never trained on the correct answers, it is just trained on multiple sequences from the problem images and still performs remarkably well.”
  • Image Compression with Neural Networks
    In “Full Resolution Image Compression with Recurrent Neural Networks”, Google expands on previous research on data compression using neural networks, exploring whether machine learning can provide better results for image compression like it has for image recognition and text summarization.