Four short links: 30 May 2016

Algorithmic Transparency, Replay Tests, Hack in the Box Presentations, and Human Perception

By Nat Torkington
May 30, 2016
  1. Algorithmic Transparency via Quantitative Input Influence: Theory and Experiments with Learning Systems (PDF) — Our empirical validation with standard machine learning algorithms demonstrates that QII measures are a useful transparency mechanism when black box access to the learning system is available. In particular, they provide better explanations than standard associative measures for a host of scenarios that we consider. Further, we show that in the situations we consider, QII is efficiently approximable and can be made differentially private while preserving accuracy. (via CMU)
  2. Why do Record/Replay Tests of Web Applications Break? (Paper a Day) — Locators caused over 73% of the test breakages we observed, and attribute-based locators caused the majority of these.
  3. Learn faster. Dig deeper. See farther.

    Join the O'Reilly online learning platform. Get a free trial today and find answers on the fly, or master something new and useful.

    Learn more
  4. Hack in the Box 2016 Presentation PDFs — be sure to check out Creating your own bad USB device.
  5. 39 Studies About Human Perception in 30 Minutes — good bootcamp in science of perception, useful for those working in UI and visualisation areas.
Post topics: Four Short Links