from Hacker News

Software That Learns by Demonstration

by Nanocurrency on 5/22/19, 7:04 PM with 2 comments

  • by latte_machiato on 5/22/19, 8:01 PM

    It's interesting to see how reinforcement learning is used to assist humans. This is a great combination of HCI and AI. Emma Brunskill at Stanford - https://cs.stanford.edu/people/ebrun - has a series of work using an RL framework to teach humans faster. For example, in this work they developed a POMDP to choose pedagogical activities that will maximize student learning, based on the student's current knowledge.
  • by jgoewert on 5/22/19, 7:12 PM

    Andrej Karpathy has a nice blog post on this: https://medium.com/@karpathy/software-2-0-a64152b37c35

    The idea is that more and more software development will be "deleting" code, and re-writing that with neural networks.