1 / 0

Introduction to Artificial Intelligence CS 260 Vanderbilt University Instructor: Douglas H. Fisher Lecture 1.2 Thinking

Introduction to Artificial Intelligence CS 260 Vanderbilt University Instructor: Douglas H. Fisher Lecture 1.2 Thinking about Thinking . Douglas H. Fisher. Thinking about Thinking . Computing as a model of thought You have likely already thought deeply about thought

wenda
Télécharger la présentation

Introduction to Artificial Intelligence CS 260 Vanderbilt University Instructor: Douglas H. Fisher Lecture 1.2 Thinking

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. Introduction to Artificial Intelligence CS 260 Vanderbilt University Instructor: Douglas H. Fisher Lecture 1.2 Thinking about Thinking Douglas H. Fisher
  2. Thinking about Thinking Computing as a model of thought You have likely already thought deeply about thought The zen (little ‘z’) of computing AI will give you additional concepts on which contemplate thought Throughout the course, think about your thinking Including the “mundane” like these examples Douglas H. Fisher
  3. Thinking about Thinking: An example In 2009, while working at the National Science Foundation (NSF), I ran into a colleague at the supermarket who had joined NSF about the same time that I had, but we had not seen each other since the initial orientation. We talked for a while about each staying a third year. I asked her what Directorate at NSF she was in, and she said “Biology, in the Division of Ecological Sciences”, and I told her that I would send her a link to a conference on societal and environmental sustainability, which included a lot of computer scientists who were addressing biodiversity issues. Douglas H. Fisher
  4. Thinking about Thinking: An example The next day, in the early afternoon, having completely forgotten about my talk with her the previous evening, the elevator stopped on the 6th floor and I looked out and saw the following text (the blue square represents the elevator door and interior): I was reminded to email my colleague. Why might this have triggered a reminding? In your explanation, think about the assumptions you are making and why they are plausible if not probable. How could you confirm (or not) assumptions if you were pushed? Douglas H. Fisher
  5. Thinking about Thinking: An example During the driving tour of the Midwest in July 2011, I took thousands of pictures with an old, non-GPS digital camera. After the trip I posted some 750 of them on Google (Picasa)  (https://picasaweb.google.com/106374191437655932029/SummerVacation2011 ). A very cool functionality is that I can locate these pictures on Google maps, using any of the modalities – maps, satellite view, street view, or Earth.  In locations with sufficient resolution I could place the photo right on the spot I was standing when I took the picture. There didn’t appear to be a way to specify orientation of the photo – what direction I was facing when I took it, but I am guessing someone will do that in the near future. Since I was placing the pictures a couple of weeks after the trip, there were different heuristics I used to place them – sometimes it was straightforward – a particular highway junction, or something otherwise named like a school or a cemetery or a mountain peak on Google maps. The order in which pictures were taken offered some constraints, since having located one picture narrowed the possible locations for the next. All of these pieces of information are things that I would want an AI system, designed to do like activity, to represent and use. Douglas H. Fisher
  6. In one case though, even with some known restricted area stemming from sequencing information, I was trying to locate a picture in the tiny town of Scribner, Nebraska, but I saw no way to identify the precise location of a picture I had taken of an old church or the like, with a steeple Douglas H. Fisher
  7. Can you identify where the building to the right is located? What information and knowledge did you use to place it? Map by Google Douglas H. Fisher
  8. Map by Google I had a shadow to work with too Douglas H. Fisher
  9. Thinking about Thinking: An Example Think about goals too, and other peoples’ actions and what that implies about their thinking. For example, I used to go to a DVD rental store to look for the movie, and found that the DVDs were always somewhat out of alphabetical order – not by a lot, but by enough that I had to do some limited search to find the title that I was looking for. One thought was that the clerks couldn’t alphabetize. Another thought was that the clerks were lazy, but my behavior over the long haul suggested there might be some intelligence behind keeping DVD titles slightly out of order. If the strategy of slightly-out-of-order DVD shelving seems explainable TO YOU as intelligent, then what tradeoffs would be involved? How might you formalize “somewhat out of order”? Would it be an intelligent strategy for a library or an online catalog or Netflix? Douglas H. Fisher
  10. (DHF) As you introspect on your thoughts and actions, ask what information/knowledge might have been relevant what environmental cues might have triggered access what processing might have occurred what goals were you pursuing
  11. Other Sources http://www.ted.com/talks/dan_ariely_asks_are_we_in_control_of_our_own_decisions.html This is a very entertaining TED video. What Ariely calls ‘irrational’, I would probably call ‘bounded rationality’ Douglas H. Fisher
More Related