Protocols from perceptual observations

Needham, Chris J.; Santos, Paulo E.; Magee, Derek R.; Devin, Vincent; Hogg, David C.; Cohn, Anthony G.

doi:10.1016/j.artint.2005.04.006

Cited by 34 publications

(25 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This indicates that the system has observed a single object of class a on the table at time t 307 , and the next recorded event was at time t 309 , which was when there were two objects on the table, one of class a and the other of class b respectively. The vision system is described in more details in [12].…”

Section: The Vision Systemmentioning

confidence: 99%

“…The purpose of the experimentation and the reporting of it here is primarily to compare and contrast descriptive and predictive approaches to learning rules from vision data. More specifically, the contribution of this paper is a comparison between Progol and HR on the task of learning protocols from visual observations reported in [12] whereas, in this earlier work, only Progol was employed. While qualitative comparisons of these systems are given in [1] and [2], this is the first quantitative comparison between them.…”

Section: Introductionmentioning

confidence: 99%

“…It is worth pointing out that, while there have been many approaches to learning from visual data (as overviewed in [12]), in this work we are interested in, first, to have access to the sound and completeness of the knowledge learned (cf. [12]) and, second, to further use the learned rules for higher level spatial and temporal reasoning, as experimented in [8].…”

Section: Introductionmentioning

confidence: 99%

“…[12]) and, second, to further use the learned rules for higher level spatial and temporal reasoning, as experimented in [8]. Thus, we chose to employ an ILP system for the learning tasks.…”

Section: Introductionmentioning

confidence: 99%

“…Towards this goal, [12] proposes a cognitive vision system capable of learning protocols from the visual information of dynamic scenes using an inductive logic programming system (ILP). In that work the predictive ILP learning system Progol [10] was used to induce theories from the visual input system.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Predictive and Descriptive Approaches to Learning Game Rules from Vision Data

Santos

Colton

Magee

2006

Advances in Artificial Intelligence - IBERAMIA-SBIA 2006

View full text Add to dashboard Cite

Abstract. Systems able to learn from visual observations have a great deal of potential for autonomous robotics, scientific discovery, and many other fields as the necessity to generalise from visual observation (from a quotidian scene or from the results of a scientific enquiry) is inherent in various domains. We describe an application to learning rules of a dice game using data from a vision system observing the game being played. In this paper, we experimented with two broad approaches: (i) a predictive learning approach with the Progol system, where explicit concept learning problems are posed and solved, and (ii) a descriptive learning approach with the HR system, where a general theory is formed with no specific problem solving task in mind and rules are extracted from the theory.

show abstract

Section: The Vision Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…[12]) and, second, to further use the learned rules for higher level spatial and temporal reasoning, as experimented in [8]. Thus, we chose to employ an ILP system for the learning tasks.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Predictive and Descriptive Approaches to Learning Game Rules from Vision Data

Santos

Colton

Magee

2006

Advances in Artificial Intelligence - IBERAMIA-SBIA 2006

View full text Add to dashboard Cite

show abstract

Qualitative modeling

Forbus

2010

WIRES Cognitive Science

View full text Add to dashboard Cite

Qualitative modeling concerns the representations and reasoning that people use to understand continuous aspects of the world. Qualitative models formalize everyday notions of causality and provide accounts of how to ground symbolic, relational representations in perceptual processes. This article surveys the basic ideas of qualitative modeling and their applications from a cognitive science perspective. It describes the basic principles of qualitative modeling, and a variety of qualitative representations that have been developed for quantities and for relationships between them, providing a kind of qualitative mathematics. Three ontological frameworks for organizing modeling knowledge (processes, components, and field) are summarized, along with research on automatically assembling models for particular tasks from such knowledge. Qualitative simulation and how it carves up time into meaningful units is discussed. We discuss several accounts of causal reasoning about dynamical systems, based on different choices of qualitative mathematics and ontology. Qualitative spatial reasoning is explored, both in terms of relational systems and visual reasoning. Applications of qualitative models of particular interest to cognitive scientists are described, including how they have been used to capture the expertise of scientists and engineers and how they have been used in education. Open questions and frontiers are also discussed, focusing on relationships between ideas developed in the qualitative modeling community and other areas of cognitive science. WIREs Cogni Sci 2011 2 374-391 DOI: 10.1002/wcs.115 For further resources related to this article, please visit the WIREs website.

show abstract

Inductive Learning Spatial Attention

Santos

2012

Encyclopedia of the Sciences of Learning

Self Cite

View full text Add to dashboard Cite

This paper investigates the automatic induction of spatial attention from the visual observation of objects manipulated on a table top. In this work, space is represented in terms of a novel observer-object relative reference system, named Local Cardinal System, defined upon the local neighbourhood of objects on the table. We present results of applying the proposed methodology on five distinct scenarios involving the construction of spatial patterns of coloured blocks.

show abstract

Protocols from perceptual observations

Cited by 34 publications

References 22 publications

Predictive and Descriptive Approaches to Learning Game Rules from Vision Data

Predictive and Descriptive Approaches to Learning Game Rules from Vision Data

Qualitative modeling

Inductive Learning Spatial Attention

Contact Info

Product

Resources

About