1 / 4

Alan Turing Celebration Lecture Biological Evolution as a Form of Learning

Alan Turing Celebration Lecture Biological Evolution as a Form of Learning Leslie Valiant, CC and Applied Math., Harvard Wed. Oct 10, 3:30pm, ECS 124

sydney
Télécharger la présentation

Alan Turing Celebration Lecture Biological Evolution as a Form of Learning

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Alan Turing Celebration Lecture Biological Evolution as a Form of Learning Leslie Valiant, CC and Applied Math., Harvard Wed. Oct 10, 3:30pm, ECS 124 Living organisms function according to protein circuits. Darwin's theory of evolution suggests that these circuits have evolved through variation guided by natural selection. However, the question of which circuits can so evolve in realistic population sizes and within realistic numbers of generations has remained essentially unaddressed.

  2. We suggest that computational learning theory offers the framework for investigating this question, of how circuits can come into being adaptively from experience, without a designer. We formulate evolution as a form of learning from examples. The targets of the learning process are the functions of highest fitness. The examples are the experiences. The learning process is constrained so that the feedback from the experiences is Darwinian. We formulate a notion of evolvability that distinguishes function classes that are evolvable with polynomially bounded resources from those that are not. The dilemma is that if the function class, say for the expression levels of proteins in terms of each other, is too restrictive, then it will not support biology, while if it is too expressive then no evolution algorithm will exist to navigate it.

  3. CSCU elections voting is available over the next 3days during the following times: • 10:00am - 3:30pm Monday, Oct. 1 • 9:30am - 3:30pm Tuesday, Oct. 2 • 9:30am - 3:30pm Wednesday, Oct. 3 Voting will be held in the CSCU office, in ECS 331. Candidate bios can be viewed just outside the office if you haven't had a chance to see their platforms. If you come vote today, you get a FREE COOKIE!

  4. CSC 482/582: Project proposal slides deadline extended to Oct. 11. You should be working on a literature review and planning your methodology.

More Related