031207 - Lecture 14 Recall Discussing early work on...

Info icon This preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Lecture 14: 03/12/2007 Recall: Discussing early work on evolutionary computation. L. Fogel in the 1960’s (evolutionary programming) Goal : evolve “machine intelligence” Focus : evolving finite-state machines for sequence prediction Sequence approx. environment Mealy Machine : eg on board last time—given an initial state and a sequence of input values, machine makes state transitions and puts out output values. For sequence prediction: {input values}={output values}={0,1} To “evaluate” a machine wrt sequence prediction / reconstruction, take initial segment of a sequence as input values; see whether ensuing output values match rest of sequence segment. There are many ways to evaluate / quantify the “degree of matching.” Fogel’s approach: have a sequence to “predict.” Start with an essentially random set of (small-ish) Melay machines; evaluate them on first, say, k symbols in sequence; keep best μ of them to be parents of next generation; create next generation as follows: 1. [genetic Г] Mutate all parents; have them on 2*μ machines 2. Evaluate these on sequence segment + next symbol 3. [selection] Retain the best μ as parents for next generation, go back to (1) *How to mutate? Change initial state Eliminate a sate and randomly reassign its incoming arrows Add a state and randomly assign its outgoing arrows (and get into
Image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern