434 Matching Annotations
  1. Jan 2017
    1. AI criticism is also limited by the accuracy of human labellers, who must carry out a close reading of the ‘training’ texts before the AI can kick in. Experiments show that readers tend to take longer to process events that are distant in time or separated by a time shift (such as ‘a day later’).
  2. Dec 2016
  3. Oct 2016
  4. Aug 2016
    1. A team at Facebook reviewed thousands of headlines using these criteria, validating each other’s work to identify a large set of clickbait headlines. From there, we built a system that looks at the set of clickbait headlines to determine what phrases are commonly used in clickbait headlines that are not used in other headlines. This is similar to how many email spam filters work.

      Though details are scarce, the very idea that Facebook would tackle this problem with both humans and algorithms is reassuring. The common argument about human filtering is that it doesn’t scale. The common argument about algorithmic filtering is that it requires good signal (though some transhumanists keep saying that things are getting better). So it’s useful to know that Facebook used so hybrid an approach. Of course, even algo-obsessed Google has used human filtering. Or, at least, human judgment to tweak their filtering algorithms. (Can’t remember who was in charge of this. Was a semi-frequent guest on This Week in Google… Update: Matt Cutts) But this very simple “we sat down and carefully identified stuff we think qualifies as clickbait before we fed the algorithm” is refreshingly clear.

  5. Jun 2016
  6. May 2016
  7. Apr 2016
    1. We should have control of the algorithms and data that guide our experiences online, and increasingly offline. Under our guidance, they can be powerful personal assistants.

      Big business has been very militant about protecting their "intellectual property". Yet they regard every detail of our personal lives as theirs to collect and sell at whim. What a bunch of little darlings they are.

  8. Feb 2016
    1. Patrick Ball—a data scientist and the director of research at the Human Rights Data Analysis Group—who has previously given expert testimony before war crimes tribunals, described the NSA's methods as "ridiculously optimistic" and "completely bullshit." A flaw in how the NSA trains SKYNET's machine learning algorithm to analyse cellular metadata, Ball told Ars, makes the results scientifically unsound.
    1. “Search is the cornerstone of Google,” Corrado said. “Machine learning isn’t just a magic syrup that you pour onto a problem and it makes it better. It took a lot of thought and care in order to build something that we really thought was worth doing.”
  9. Jan 2016
  10. Dec 2015
  11. Nov 2015
    1. a study by Stephen Schueller, published last year in the Journal of Positive Psychology, found that people assigned to a happiness activity similar to one for which they previously expressed a preference showed significantly greater increases in happiness than people assigned to an activity not based on a prior preference. This, writes Schueller, is “a model for positive psychology exercises similar to Netflix for movies or Amazon for books and other products.”

      The study.

    1. TPOT is a Python tool that automatically creates and optimizes machine learning pipelines using genetic programming. Think of TPOT as your “Data Science Assistant”: TPOT will automate the most tedious part of machine learning by intelligently exploring thousands of possible pipelines, then recommending the pipelines that work best for your data.

      https://github.com/rhiever/tpot TPOT (Tree-based Pipeline Optimization Tool) Built on numpy, scipy, pandas, scikit-learn, and deap.

    1. Nanodegree Program Summary Machine learning represents a key evolution in the fields of computer science, data analysis, software engineering, and artificial intelligence. It has quickly become industry's preferred way to make sense of the staggering volume of data our modern world produces. Machine learning engineers build programs that dynamically perform the analyses that data scientists used to perform manually. These programs can “learn” based on millions of experiences, all rigorously and numerically defined.
  12. Oct 2015
    1. I have the feeling we do not need to use models as complicated as some outlined in the text; we can (and finally will have to) abstract from most of the issues we can imagine. I expect that "magic" (an undisclosed heuristic, perhaps in combination with machine learning) will deal with the issues, a black box that will be considered inherently flawed and practical enough at the same time. The results from experimental ethics can help form the heuristic while the necessity for easy implementation and maintainability will limit the applications significantly.

  13. Sep 2015
  14. Aug 2015
  15. Jul 2015
  16. Jun 2015
    1. Enter the Daily Mail website, MailOnline, and CNN online. These sites display news stories with the main points of the story displayed as bullet points that are written independently of the text. “Of key importance is that these summary points are abstractive and do not simply copy sentences from the documents,” say Hermann and co.

      Someday, maybe projects like Hypothesis will help teach computers to read, too.

  17. Jan 2015
  18. Nov 2014
  19. Aug 2014