Presentation is loading. Please wait.

Presentation is loading. Please wait.

Learning Achieving AI via Learning: an old dream; recent results L. Manevitz All rights reserved.

Similar presentations


Presentation on theme: "Learning Achieving AI via Learning: an old dream; recent results L. Manevitz All rights reserved."— Presentation transcript:

1 Learning Achieving AI via Learning: an old dream; recent results L. Manevitz All rights reserved

2 How does a baby gain intelligence (as measured by Turing Test)? Some things are “ programmed in ” (smiling, crying, feeling). Language, problem solving however seem to be learned. How is this done? possible?.

3 An Old Idea: Design a “ Baby ” with LEARNING capabilities and let it achieve AI by itself Several Different Giant Projects around the world in this direction CYC Project of Doug Lenat CYBORG Project of Rodney Brooks.

4 CYC Project Basic Idea; develop “ common sense ” by cataloging huge number of basic facts and “ scripts ” so that information available in “ intelligent ” fashion immediately with graceful degradation. Learning involves acquiring new facts and scripts.

5 Cyborg Project True learning from “ ground zero ”. Idea that intelligence integrally bound in learning and in the physical structure of the artifact. Thus making “ human like ” robot; where learning is by interplay with other humans.

6 Underlying Learning Ideas These projects use a variety of learning techniques. Today we will briefly describe a few of them.

7 Some Learning Techniques Concept Learning By Examples Learning By Building Identification Tree (ID3) Parameter Learning (reinforcement learning) Parameter Learning (Neural Networks and Perceptrons)

8 Concept Learning (Using Teacher) Suppose we are in the world of blocks. Suppose we have a huge object oriented data base using inheritance of different types which tells us information about different kinds of blocks (e.g. default information; weight calculation, and so on).

9 Suppose we would like to learn a new “ concept ” ; say that of an “ arch ”. A teacher can then give examples of both arches; and non-arches and by this way guide the “ student ”, I.e. the program to add to its data base the new concept of arch. This requires various heuristics.

10 Basic Algorithm Start Initial Concept with First Positive Example For each subsequent example –If “ non-example ” use SPECIALIZE –If positive example use GENERALIZE NOTE: Order of examples determined by TEACHER

11 Specialize Match Negative Example to Concept Model Find single, “ most important ” difference between example and concept –If not identifiable, ignore example –If example has link lacking in model use “ forbid link ” heuristic –If model has link lacking in example use “ require link ” heuristic

12 Arch Example Support Left of

13 Generalize Match Positive Example to Concept Model For each difference : –If link points to different classes in example and model If classes part of classification tree, use “ climb-tree ” heuristic If classes form exhaustive set, use “ drop-link ” Otherwise, use “ enlarge set ” heuristic –If link missing in example, use “ drop-link ” heuristic –If different numerical values use “ close-interval ” heuristic

14 Require Link Forbid Link Climb Tree Enlarge Set Drop Link Close Interval Some Heuristics (following Winston ’ s presentation)

15 Arch Learning

16 Show evolution of model Follow Winston development


Download ppt "Learning Achieving AI via Learning: an old dream; recent results L. Manevitz All rights reserved."

Similar presentations


Ads by Google