A Multi-Level Organization of Semantic Primitives for Learning Models of Environment Autonomously from Continuous Data for Design (Extended Abstract)
BibTeX
@MISC{Prabhakar_amulti-level,
author = {S. Prabhakar and Sattiraju Prabhakar and Greg Smith},
title = {A Multi-Level Organization of Semantic Primitives for Learning Models of Environment Autonomously from Continuous Data for Design (Extended Abstract)},
year = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
) Sattiraju Prabhakar and Greg Smith School of Computing Sciences University of Technology, Sydney PO Box 123, Broadway, NSW 2007, Australia Email: {prabhaka, gjsmith}@socs.uts.edu.au Autonomous Design Agent In this paper, we present an overview of the project on Autonomous Learning Design Agents which began recently. An agent that addresses the task of Design by Autonomous Learning (DAL) builds an abstract model of the environment from the sensory data with the goal to modify the environment to meet a new set of functionalities. Any agent that addresses the DAL task is confronted with a task of transforming the underlying causes that produce the continuous data of the environment to produce another set of continuous data. In our work, we explore the possibility of such a transformation through a hierarchical order of discretizations each of which allows the agent to act differently, and yet allows the agent to draw some global conclusions. The machine learning research has identifi...
Citations
| 129 | Vision, Instruction and Action - Chapman - 1991 |
| 103 | Map learning with uninterpreted sensors and effectors - Pierce, Kuipers - 1997 |
| 85 | Autonomous Learning from the Environment - Shen - 1994 |
| 22 | Generic object recognition using form and functionMachine Perception and - Stark, Bowyer - 1996 |
| 22 | Understanding complex dynamics by visual and symbolic reasoning - Yip - 1991 |
| 12 | Creating design objects from cases for interactive spatial composition - Smith, Stalker, et al. - 1996 |
| 8 | Spatial aggregation: Modeling and controlling physical fields - Bailey-Kellogg, Zhao - 1997 |
| 6 | Feature Discovery for Inductive Concept Learning - Fawcett - 1993 |
| 1 | Compositional Constructive Induction: Discovering Topological Features of Environmental Changes from Vision Data - Prabhakar - 1999 |
