Art Imitates Life: Programming by Example as an Imitation Game
نویسنده
چکیده
Having the computer imitate recorded human actions is the basis for an experimental technology for programming, variously called "Programming by Example" or "Programming by Demonstration". This is an under-appreciated technology that holds the promise of revolutionizing programming and making it more accessible, especially to non-expert programmers. Because imitation is a natural learning strategy for people, it can help alleviate the barriers of abstraction and lack of short-term memory that makes programming difficult for people. Much past work has focused on how to represent the recorded actions, and how to generalize the resulting procedures so that they can be applicable to examples analogous to those on which the system is taught. This chapter will survey past work in the field and speculate on how the mechanics of imitative behavior might inform future developments, especially the feedback loop of verifying that imitative behavior has the desired result in new situations.
منابع مشابه
Multiobjective security game with fuzzy payoffs
A multiobjective security game problem with fuzzy payoffs is studied in this paper. The problem is formulated as a bilevel programming problem with fuzzy coefficients. Using the idea of nearest interval approximation of fuzzy numbers, the problem is transformed into a bilevel programming problem with interval coefficients. The Karush-Kuhn-Tucker conditions is applied then to reduce the problem ...
متن کاملObtaining a possible allocation in the bankruptcy model using the Shapley value
Data envelopment analysis (DEA) is an effective tool for supporting decision-makers to assess bankruptcy, uncertainty concepts including intervals, and game theory. The bankruptcy problem with the qualitative parameters is an economic problem under uncertainty. Accordingly, we combine the concepts of the DEA game theory and uncertain models as interval linear programming (ILP), which can be app...
متن کاملAn interval-valued programming approach to matrix games with payoffs of triangular intuitionistic fuzzy numbers
The purpose of this paper is to develop a methodology for solving a new type of matrix games in which payoffs are expressed with triangular intuitionistic fuzzy numbers (TIFNs). In this methodology, the concept of solutions for matrix games with payoffs of TIFNs is introduced. A pair of auxiliary intuitionistic fuzzy programming models for players are established to determine optimal strategies...
متن کاملA new approach for learning postures: an imitation game between a human and a robot
In this paper, we investigate a sensory-motor architecture allowing a robot to learn to recognize postures. The learning is performed without a teaching signal that associates a specific posture with the robot’s motor internal state. Our architecture assumes that the robot initially performs postures, then the human imitates them. An on-line learning scheme without an explicit reward or ad-hoc ...
متن کاملMultiple attribute decision making with triangular intuitionistic fuzzy numbers based on zero-sum game approach
For many decision problems with uncertainty, triangular intuitionistic fuzzy number is a useful tool in expressing ill-known quantities. This paper develops a novel decision method based on zero-sum game for multiple attribute decision making problems where the attribute values take the form of triangular intuitionistic fuzzy numbers and the attribute weights are unknown. First, a new value ind...
متن کامل