Learn sesame - A learning agent engine

被引:10
作者
Caglayan, A
Snorrason, M
Jacoby, J
Mazzu, J
Jones, R
Kumar, K
机构
[1] Charles River Analytics, Cambridge, MA
关键词
D O I
10.1080/088395197118109
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Open Sesame(R) 1.0-released in 1993-was the world's first commercial user interface learning agent. The development of this agent involved a number of decisions about basic design issues that had not been previously addressed, including the expected types of agents and the preferred form and frequency of interaction. Irt the 2 years after shipping Open Sesame! 1.0, we have compiled a rich database of customer feedback. Many of our design choices have been validated by the general approval of our customers, while same were not received as favorably. Thanks to the overwhelming amount of feedback, we were able to substantially improve the design for Open Sesame 2.0 and develop a cross-platform learning engine-Learn Sesame-that can be used to add learning agent functionality to any third-party application. In this article, we present a summary of the lessons learned from customer feedback, an outline of resulting design changes, the details of the developed learning agent engine, and planned research.
引用
收藏
页码:393 / 412
页数:20
相关论文
共 11 条
  • [1] CAGLAYAN A, 1993, WORLD C NEUR NETW PO
  • [2] ART 2-A - AN ADAPTIVE RESONANCE ALGORITHM FOR RAPID CATEGORY LEARNING AND RECOGNITION
    CARPENTER, GA
    GROSSBERG, S
    ROSEN, DB
    [J]. NEURAL NETWORKS, 1991, 4 (04) : 493 - 504
  • [3] KUMAR K, 1996, SMARTS OPEN SESAME C
  • [4] Laurel B., 1990, ART HUMAN COMPUTER I
  • [5] LIEBOWITZ J, 1993, BYTE JUL
  • [6] MAES P, 1993, INT WORKSH INT US IN
  • [7] MAZZU JM, 1991, MAT AD STRUCT C AL V
  • [8] MAZZU JM, 1994, HYBRID INTELLIGENCE
  • [9] NASS CI, 1993, CHI C BOST MASS
  • [10] NORMAN TJ, 1994, GOAL CREATION MOTIVA