Helping students soar to success on computers: An investigation of the SOAR study method for computer-based learning.

This study used self-report and observation techniques to investigate how students study computer-based materials. In addition, it examined if a study method called SOAR can facilitate computer-based learning. SOAR is an acronym that stands for the method's 4 theoretically driven and empirically supported components: select (S), organize (O), associate (A), and regulate (R). There were 2 experiments. In Experiment 1, 114 undergraduates completed a questionnaire about how they study computer-based materials. Students reported using more ineffective study strategies than effective SOAR strategies. In Experiment 2, 108 different undergraduates read an online text about wildcats and then created materials that reflected their preferred study method, the full SOAR method, or parts of the SOAR method. Specifically, the control group created their preferred study notes; the S group created a complete set of linear notes; the SO group created graphically organized matrix notes; the SOA group created a matrix and associations; and the SOAR group created a matrix, associations, and practice questions that aid self-regulation. The SOAR materials were also created in line with four theoretical principles for technology design (Mayer, 2009). Students studied their materials in preparation for fact and relationship tests. Results from both tests showed that those using the full SOAR method outscored the control group and most other groups using parts of the SOAR method. In addition, observations of students' preferred study methods confirmed the Experiment 1 self-reports that unaided students use ineffective study strategies. Study limitations, suggestions for future research, and instructional implications are presented. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Evaluation of complex and dynamic safety tasks in human learning using the ACT-R and SOAR skill acquisition theories

This paper provides a human-centered analytical approach to learning dynamic and complex tasks using the Adaptive Control of Thought-Rational (ACT-R) and the State, Operator And Result (SOAR) models by comparing the task times of the model and the subjects. Twenty-one full time assembly line workers at a local computer company (14 men and 7 women) from ages 18-32 (Mean = 19.86 years, SD = 0.96 years) were randomly selected for this analysis. The task involved the placement of printed circuit board (PCB) components on the flow line of the desktop computer mother board manufacturing process. The overall timed performance of the subjects indicated that the match between the model and the subjects was good, resulting in an R² - value of 0.94. At the unit task level performance, and R² - value of 0.96 for placing the PCBs on the flow line. For tasks involving picking and searching of PCBs, the obtained R² - value was 0.76 and R² of 0.68 at the keystroke level. Findings revealed that the model already started out with a complete strategy of performing the task, whereas the human participants had to acquire additional learning information during the trials. Efforts will be made in the future to determine how the performance of the human subjects could be enhanced to meet or the same level as the model performance.     

基于符号主义范式统一认知模型的分析与研究

认知科学已成为21世纪智力革命的前沿.阐述认知科学符号主义范式统一认知模型--状态算子和结果SOAR(State operator and result)和思维的适应控制ACT(Adaptive Control of Thought),在此基础上结合信念系统模型,提出一个更加系统、全面的认知模型.     

COSA – A generic cognitive system architecture based on a cognitive model of human behavior

This article presents an overview of COSA, a cognitive system architecture, which is a generic framework proposing a unified architecture for cognitive systems. Conventional automation and similar systems lack the ability of cooperation and cognition, leading to serious deficiencies when acting in complex environments, especially in the context of human-computer interaction. Cognitive systems based on cognitive automation can overcome these deficiencies. Designing such artificial cognitive systems can be considered a very complex software development process. Although a number of developments of artificial cognitive systems have already demonstrated great functional potentials in field tests, the engineering approach of this kind of software is still a candidate for further improvement. Therefore, wide-spread application of cognitive systems has not been achieved yet. This article presents a new engineering approach for cognitive systems, implemented by the COSA framework, which may be a crucial step forward to achieve a wide-spread application of cognitive systems. The approach is based on a new concept of generating cognitive behaviour, the cognitive process (CP). The CP can be regarded as a model of the human information processing loop whose behaviour is solely driven by "a-priori knowledge". The main features of COSA are the implementation of the CP as its kernel and the separation of architecture from application leading to reduced development time and increased knowledge reuse. Additionally, separating the knowledge modelling process from behaviour generation enables the knowledge designer to use the knowledge representation that is best suited to his modelling problem. A first application based on COSA implements an autonomous unmanned air vehicle accomplishing a military reconnaissance mission. Some of the application experiences with the new approach are presented.     

On-Line Learning from Search Failures

Learning by explaining failures and avoiding similar ones thereafter is an attractive way to speed up problem solving. However, previous methods for explanation-based learning from failure can take too long to detect failures, explain them, or test the learned rules. This expense is especially critical for adaptive search, in which control knowledge acquired while solving an individual problem instance must be learned quickly enough to speed up its solution.We present an adaptive search technique that speeds up state-space search by learning heuristic censors while searching. The censors speed up search by pruning away more and more of the space until a solution is found in the pruned space. Censors are learned by explaining dead ends and other search failures. To learn quickly, the technique overgeneralizes by assuming that certain constraints are preservable, i.e., remain true along at least one solution path. A recovery mechanism detects violations of this assumption and selectively relaxes learned censors. The technique, implemented in an adaptive problem solver named FAILSAFE-2, learns useful heuristics that cannot be learned by other reported methods.We present experimental evidence that FAILSAFE-2 is effective (learns useful rules, even in recursive domains where PRODIGY and STATIC do not), adaptive (learns fast enough to pay off even within a single problem), and general (speeds up diverse problem solvers, even initially strong ones).     

认知引擎中案例学习模块的设计与实现

学习能力是认知无线电区别于现有电台的最主要特征,研究基于SOAR架构的案例学习功能在已有认知引擎平台中的设计与实现。首先介绍了人工智能开发工具SOAR的基本原理与概念,进而在认知无线电原型系统平台上,设计并实现了基于SOAR架构的,具备案例学习能力的认知学习模块。具备案例学习能力的认知引擎使认知无线电系统具备从以往经验中获取知识的能力,提高了其在未来任务中的决策性能。