Pub Date : 1996-12-15DOI: 10.1080/10447319609526160
James A. Balliett, M. Dainoff, L. Mark
Two experiments investigated the effect of upper extremity posture on reported discomfort in the shoulder‐neck region. In Experiment 1, 12 participants worked in two postures that only differed in the position of the arms. The 7° posture” required 7° of upper arm flexion and a 90° upper arm‐forearm angle. The “30° posture” required 30° of upper arm flexion and a 90° upper arm‐forearm angle. Location and intensity of discomfort were reported every 5 min while participants performed a simple tracking task at the computer. Experiment 2 was identical to the first except participants worked in one of the postures for both work sessions. The 30° posture generally resulted in more frequent and intense reports of shoulder‐neck discomfort than the 7° posture. However, the 7° posture was not nearly as effective when it was assumed after the 30° posture. The implications of such carry over effects for VDT work in a seated posture are discussed.
{"title":"The effect of degree of upper arm flexion on shoulder-neck discomfort at the VDT","authors":"James A. Balliett, M. Dainoff, L. Mark","doi":"10.1080/10447319609526160","DOIUrl":"https://doi.org/10.1080/10447319609526160","url":null,"abstract":"Two experiments investigated the effect of upper extremity posture on reported discomfort in the shoulder‐neck region. In Experiment 1, 12 participants worked in two postures that only differed in the position of the arms. The 7° posture” required 7° of upper arm flexion and a 90° upper arm‐forearm angle. The “30° posture” required 30° of upper arm flexion and a 90° upper arm‐forearm angle. Location and intensity of discomfort were reported every 5 min while participants performed a simple tracking task at the computer. Experiment 2 was identical to the first except participants worked in one of the postures for both work sessions. The 30° posture generally resulted in more frequent and intense reports of shoulder‐neck discomfort than the 7° posture. However, the 7° posture was not nearly as effective when it was assumed after the 30° posture. The implications of such carry over effects for VDT work in a seated posture are discussed.","PeriodicalId":208962,"journal":{"name":"Int. J. Hum. Comput. Interact.","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124572626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1996-12-01DOI: 10.1080/10447319609526138
G. Burdea, P. Richard, P. Coiffet
Virtual reality (VR) involves multimodal interactions with computer‐simulated worlds through visual, auditory, and haptic feedback. This article reviews the state of the art in special‐purpose input‐output devices, such as trackers, sensing gloves, 3‐D audio cards, stereo displays, and haptic feedback masters. The integration of these devices in local and network‐distributed VR simulation systems is subsequently discussed. Finally, we present human‐factor studies that quantify the benefits of several feedback modalities on simulation realism and sensorial immersion. Specifically, we consider tracking and dextrous manipulation task performance in terms of error rates and learning times when graphics, audio, and haptic feedback are provided.
{"title":"Multimodal virtual reality: Input-output devices, system integration, and human factors","authors":"G. Burdea, P. Richard, P. Coiffet","doi":"10.1080/10447319609526138","DOIUrl":"https://doi.org/10.1080/10447319609526138","url":null,"abstract":"Virtual reality (VR) involves multimodal interactions with computer‐simulated worlds through visual, auditory, and haptic feedback. This article reviews the state of the art in special‐purpose input‐output devices, such as trackers, sensing gloves, 3‐D audio cards, stereo displays, and haptic feedback masters. The integration of these devices in local and network‐distributed VR simulation systems is subsequently discussed. Finally, we present human‐factor studies that quantify the benefits of several feedback modalities on simulation realism and sensorial immersion. Specifically, we consider tracking and dextrous manipulation task performance in terms of error rates and learning times when graphics, audio, and haptic feedback are provided.","PeriodicalId":208962,"journal":{"name":"Int. J. Hum. Comput. Interact.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130580728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1996-10-01DOI: 10.1080/10447319609526162
E. Hoekstra, J. Hurrell, N. Swanson, A. Tepper
A cross‐sectional study was conducted to evaluate the association between work‐related musculoskeletal disorders (WRMDs) and work conditions, perceived exhaustion, job dissatisfaction, and job‐stress issues at two teleservice centers (TSCs). The study covered teleservice representatives who respond to toll‐free calls for assistance. The work involves a computer or manual search for information, and data entry using keyboards. One facility had upgraded the furniture at the workstations; the other facility had not. A questionnaire survey among 114 teleservice representatives and an ergonomic evaluation were conducted to determine WRMDs and their risk factors and perceived job stress. A high prevalence of symptoms of WRMDs was found at both TSCs. Suboptimal ergonomic conditions were associated with neck, shoulder, elbow, and back WRMDs, as well as with increased job dissatisfaction. Perceived increased workload variability and lack of job control were associated with the occurrence of neck and back WRMDs, re...
{"title":"Ergonomic, job task, and psychosocial risk factors for work-related musculoskeletal disorders among teleservice center representatives","authors":"E. Hoekstra, J. Hurrell, N. Swanson, A. Tepper","doi":"10.1080/10447319609526162","DOIUrl":"https://doi.org/10.1080/10447319609526162","url":null,"abstract":"A cross‐sectional study was conducted to evaluate the association between work‐related musculoskeletal disorders (WRMDs) and work conditions, perceived exhaustion, job dissatisfaction, and job‐stress issues at two teleservice centers (TSCs). The study covered teleservice representatives who respond to toll‐free calls for assistance. The work involves a computer or manual search for information, and data entry using keyboards. One facility had upgraded the furniture at the workstations; the other facility had not. A questionnaire survey among 114 teleservice representatives and an ergonomic evaluation were conducted to determine WRMDs and their risk factors and perceived job stress. A high prevalence of symptoms of WRMDs was found at both TSCs. Suboptimal ergonomic conditions were associated with neck, shoulder, elbow, and back WRMDs, as well as with increased job dissatisfaction. Perceived increased workload variability and lack of job control were associated with the occurrence of neck and back WRMDs, re...","PeriodicalId":208962,"journal":{"name":"Int. J. Hum. Comput. Interact.","volume":"38 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124183017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1996-08-01DOI: 10.1080/10447319609526149
V. Moustakis
This special issue is devoted to invited articles on machine learning (ML). Most of the articles included in this issue were also presented in a special session on ML at the 8th International Conference on Human-Compute r Interaction that was held at Yokohama, Japan in July 1995 (Anzai, Ogawa, & Mori, 1995). Since the publication of the first volume of Machine Learning: An Artificial Intelligence Approach (Michalski, Carbonell, & Mitchell, 1983), ML has progressed significantly and several applications have been reported, whereas several others have remained unpublished. In the same volume, the Nobel prize winner Herbert A. Simon places ML in context with learning by stating that learning denotes changes in the system that are adaptive in the sense that they enable the system to do the same task or tasks drawn from the same population more efficiently and more effectively the next time. Many scientific journals and international conferences have hosted special sections and sessions reporting on ML or on applications of ML. Knowledge acquisition, planning, scheduling, decision support, transportation, medicine, and engineering, among others, compose the domains in which ML has been both applied, proved effective, and continues to do so. An attempt to review all ML applications or theory developments would render this introduction or even the special issue endless. In part, a goal of this issue is to extend hands between the two communities: human-computer interaction (HCI) and ML. To a large degree, both share a common goal: Each one tries to improve the human performance and adaptability to changing conditions of some system. Enhancing systems with learning ability may prove conducive to building better systems. Humans come in life with built-in learning potential and excluding artifacts from learning may seriously impede user acceptability of new technology. The article by Moustakis, Lehto, and Salvendy captures expert judgment about a critical question: Which ML method should be used for a given task? The article is based on an extensive survey of ML experts and statistical analysis of responses. It also kicks off the special issue because it briefly introduces the reader to the various ML methods and tasks in which ML may be used. The article by Yoshida and Motoda presents a framework for using ML to automate user modeling and behavior in a user adaptive interface system. It uses
{"title":"Introduction: ML meets HCI","authors":"V. Moustakis","doi":"10.1080/10447319609526149","DOIUrl":"https://doi.org/10.1080/10447319609526149","url":null,"abstract":"This special issue is devoted to invited articles on machine learning (ML). Most of the articles included in this issue were also presented in a special session on ML at the 8th International Conference on Human-Compute r Interaction that was held at Yokohama, Japan in July 1995 (Anzai, Ogawa, & Mori, 1995). Since the publication of the first volume of Machine Learning: An Artificial Intelligence Approach (Michalski, Carbonell, & Mitchell, 1983), ML has progressed significantly and several applications have been reported, whereas several others have remained unpublished. In the same volume, the Nobel prize winner Herbert A. Simon places ML in context with learning by stating that learning denotes changes in the system that are adaptive in the sense that they enable the system to do the same task or tasks drawn from the same population more efficiently and more effectively the next time. Many scientific journals and international conferences have hosted special sections and sessions reporting on ML or on applications of ML. Knowledge acquisition, planning, scheduling, decision support, transportation, medicine, and engineering, among others, compose the domains in which ML has been both applied, proved effective, and continues to do so. An attempt to review all ML applications or theory developments would render this introduction or even the special issue endless. In part, a goal of this issue is to extend hands between the two communities: human-computer interaction (HCI) and ML. To a large degree, both share a common goal: Each one tries to improve the human performance and adaptability to changing conditions of some system. Enhancing systems with learning ability may prove conducive to building better systems. Humans come in life with built-in learning potential and excluding artifacts from learning may seriously impede user acceptability of new technology. The article by Moustakis, Lehto, and Salvendy captures expert judgment about a critical question: Which ML method should be used for a given task? The article is based on an extensive survey of ML experts and statistical analysis of responses. It also kicks off the special issue because it briefly introduces the reader to the various ML methods and tasks in which ML may be used. The article by Yoshida and Motoda presents a framework for using ML to automate user modeling and behavior in a user adaptive interface system. It uses","PeriodicalId":208962,"journal":{"name":"Int. J. Hum. Comput. Interact.","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128213569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1996-08-01DOI: 10.1080/10447319609526155
K. Hiraki, Y. Anzai
Intelligent robots need to share knowledge with human beings for flexible interaction. However, the gap between low‐level sensory data and abstract human knowledge makes it difficult to preencode robot behavior against human's various complex demands. This article presents a way of enabling robots to learn abstract concepts from sensory and perceptual data. In order to overcome the gap between the low‐level sensory data and higher level concept description, a method called feature abstraction is used. Feature abstraction dynamically defines abstract sensors from primitive sensory devices and makes it possible to learn appropriate sensory‐motor constraints. This method has been implemented on a real mobile robot as a learning system called Acorn‐II. Acorn‐II was evaluated with some empirical results and it was shown that the system can learn some abstract concepts more accurately than other existing systems.
{"title":"Sharing knowledge with robots","authors":"K. Hiraki, Y. Anzai","doi":"10.1080/10447319609526155","DOIUrl":"https://doi.org/10.1080/10447319609526155","url":null,"abstract":"Intelligent robots need to share knowledge with human beings for flexible interaction. However, the gap between low‐level sensory data and abstract human knowledge makes it difficult to preencode robot behavior against human's various complex demands. This article presents a way of enabling robots to learn abstract concepts from sensory and perceptual data. In order to overcome the gap between the low‐level sensory data and higher level concept description, a method called feature abstraction is used. Feature abstraction dynamically defines abstract sensors from primitive sensory devices and makes it possible to learn appropriate sensory‐motor constraints. This method has been implemented on a real mobile robot as a learning system called Acorn‐II. Acorn‐II was evaluated with some empirical results and it was shown that the system can learn some abstract concepts more accurately than other existing systems.","PeriodicalId":208962,"journal":{"name":"Int. J. Hum. Comput. Interact.","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127706185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1996-08-01DOI: 10.1080/10447319609526154
Y. Sakakibara, Kazuo Misue, Takeshi Koshiba
The rapid growth of data in large databases, such as text databases and scientific databases, requires efficient computer methods for automating analyses of the data with the goal of acquiring knowledges or making discoveries. Because the analyses of data are generally so expensive, most parts in databases remains as raw, unanalyzed primary data. Technology from machine learning (ML) will offer efficient tools for the intelligent analyses of the data using generalization ability. Generalization is an important ability specific to inductive learning that will predict unseen data with high accuracy based on learned concepts from training examples. In this article, we apply ML to text‐database analyses and knowledge acquisitions from text databases. We propose a completely new approach to the problem of text classification and extracting keywords by using ML techniques. We introduce a class of representations for classifying text data based on decision trees; (i.e., decision trees over attributes on strings)...
{"title":"A machine learning approach to knowledge acquisitions from text databases","authors":"Y. Sakakibara, Kazuo Misue, Takeshi Koshiba","doi":"10.1080/10447319609526154","DOIUrl":"https://doi.org/10.1080/10447319609526154","url":null,"abstract":"The rapid growth of data in large databases, such as text databases and scientific databases, requires efficient computer methods for automating analyses of the data with the goal of acquiring knowledges or making discoveries. Because the analyses of data are generally so expensive, most parts in databases remains as raw, unanalyzed primary data. Technology from machine learning (ML) will offer efficient tools for the intelligent analyses of the data using generalization ability. Generalization is an important ability specific to inductive learning that will predict unseen data with high accuracy based on learned concepts from training examples. In this article, we apply ML to text‐database analyses and knowledge acquisitions from text databases. We propose a completely new approach to the problem of text classification and extracting keywords by using ML techniques. We introduce a class of representations for classifying text data based on decision trees; (i.e., decision trees over attributes on strings)...","PeriodicalId":208962,"journal":{"name":"Int. J. Hum. Comput. Interact.","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126463154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1996-08-01DOI: 10.1080/10447319609526156
E. D. Heijer, P. Adriaans
In this article, we present experiences with the Crew Availability Planning and Training System (CAPTAINS). CAPTAINS is a complex planning‐aid system that assists professional career planners. This article describes the learning component of CAPTAINS—the Learning Classifier System (LCS)—which predicts the bids on functions of pilots. We also present experiments with the LCS and their results.
{"title":"The application of genetic algorithms in a career planning environment: CAPTAINS","authors":"E. D. Heijer, P. Adriaans","doi":"10.1080/10447319609526156","DOIUrl":"https://doi.org/10.1080/10447319609526156","url":null,"abstract":"In this article, we present experiences with the Crew Availability Planning and Training System (CAPTAINS). CAPTAINS is a complex planning‐aid system that assists professional career planners. This article describes the learning component of CAPTAINS—the Learning Classifier System (LCS)—which predicts the bids on functions of pilots. We also present experiments with the LCS and their results.","PeriodicalId":208962,"journal":{"name":"Int. J. Hum. Comput. Interact.","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121634586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1996-08-01DOI: 10.1080/10447319609526150
V. Moustakis, M. Lehto, G. Salvendy
Determining the most appropriate Machine Learning (ML) method, system, or algorithm for a particular application is not trivial. This article reports on a survey of 103 experts specializing in ML who were asked to rate ML method appropriateness to intelligent tasks. Ratings were captured via a structured questionnaire including 12 ML methods and 9 task categories. Results showed that the experts mapped particular ML methods to task categories. Factor analysis revealed three fundamental factors, which explained most of the variance in the expert ratings. Machine learning methods could be grouped on the basis of these factors into six application categories, wherein one or more methods were deemed most appropriate by the evaluated group of experts. This, in turn, concludes that cooperation between alternative ML methods may be necessary to support one or more intelligent tasks.
{"title":"Survey of expert opinion: Which machine learning method may be used for which task?","authors":"V. Moustakis, M. Lehto, G. Salvendy","doi":"10.1080/10447319609526150","DOIUrl":"https://doi.org/10.1080/10447319609526150","url":null,"abstract":"Determining the most appropriate Machine Learning (ML) method, system, or algorithm for a particular application is not trivial. This article reports on a survey of 103 experts specializing in ML who were asked to rate ML method appropriateness to intelligent tasks. Ratings were captured via a structured questionnaire including 12 ML methods and 9 task categories. Results showed that the experts mapped particular ML methods to task categories. Factor analysis revealed three fundamental factors, which explained most of the variance in the expert ratings. Machine learning methods could be grouped on the basis of these factors into six application categories, wherein one or more methods were deemed most appropriate by the evaluated group of experts. This, in turn, concludes that cooperation between alternative ML methods may be necessary to support one or more intelligent tasks.","PeriodicalId":208962,"journal":{"name":"Int. J. Hum. Comput. Interact.","volume":"182 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123719191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1996-08-01DOI: 10.1080/10447319609526153
J. Herrmann
Intelligent assistant systems provide an adequate organization of human‐computer interaction for complex problem solving. These knowledge‐based systems are characterized by a cooperative problem‐solving procedure. User and system cooperate intensively to produce the aimed result. Machine learning methods can provide significant support for assistant systems. In this article, it is pointed out how assistant systems can be supported in various ways. For instance, machine learning methods can extend, revise, optimize, and adapt the knowledge base of an assistant system. In this way, they can contribute to the utility and maintainability of an intelligent assistant system. They can also increase the flexibility and effectiveness of human‐computer interaction. The learning apprentice system COSIMA is presented which acquires knowledge about single problem‐solving steps from observation of the user. Production rules for floorplanning, a sub‐task of VLSI design, are acquired and refined cooperatively by differen...
{"title":"Different ways to support intelligent assistant systems by use of machine learning methods","authors":"J. Herrmann","doi":"10.1080/10447319609526153","DOIUrl":"https://doi.org/10.1080/10447319609526153","url":null,"abstract":"Intelligent assistant systems provide an adequate organization of human‐computer interaction for complex problem solving. These knowledge‐based systems are characterized by a cooperative problem‐solving procedure. User and system cooperate intensively to produce the aimed result. Machine learning methods can provide significant support for assistant systems. In this article, it is pointed out how assistant systems can be supported in various ways. For instance, machine learning methods can extend, revise, optimize, and adapt the knowledge base of an assistant system. In this way, they can contribute to the utility and maintainability of an intelligent assistant system. They can also increase the flexibility and effectiveness of human‐computer interaction. The learning apprentice system COSIMA is presented which acquires knowledge about single problem‐solving steps from observation of the user. Production rules for floorplanning, a sub‐task of VLSI design, are acquired and refined cooperatively by differen...","PeriodicalId":208962,"journal":{"name":"Int. J. Hum. Comput. Interact.","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122436378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1996-08-01DOI: 10.1080/10447319609526152
G. Tecuci, M. Hieb
The ability to build intelligent agents is significantly constrained by the knowledge acquisition effort required. Many iterations by human experts and knowledge engineers are currently necessary to develop knowledge‐based agents with acceptable performance. We have developed a novel approach, called Disciple, for building intelligent agents that relies on an interactive tutoring paradigm, rather than the traditional knowledge engineering paradigm. In the Disciple approach, an expert teaches an agent through five basic types of interactions. Such rich interaction is rare among machine learning (ML) systems, but is necessary to develop more powerful systems. These interactions, from the point of view of the expert, include specifying knowledge to the agent, giving the agent a concrete problem and its solution that the agent is to learn a general rule for, validating analogical problems and solutions proposed by the agent, explaining to the agent reasons for the validation, and being guided to provide new k...
{"title":"Teaching intelligent agents: The disciple approach","authors":"G. Tecuci, M. Hieb","doi":"10.1080/10447319609526152","DOIUrl":"https://doi.org/10.1080/10447319609526152","url":null,"abstract":"The ability to build intelligent agents is significantly constrained by the knowledge acquisition effort required. Many iterations by human experts and knowledge engineers are currently necessary to develop knowledge‐based agents with acceptable performance. We have developed a novel approach, called Disciple, for building intelligent agents that relies on an interactive tutoring paradigm, rather than the traditional knowledge engineering paradigm. In the Disciple approach, an expert teaches an agent through five basic types of interactions. Such rich interaction is rare among machine learning (ML) systems, but is necessary to develop more powerful systems. These interactions, from the point of view of the expert, include specifying knowledge to the agent, giving the agent a concrete problem and its solution that the agent is to learn a general rule for, validating analogical problems and solutions proposed by the agent, explaining to the agent reasons for the validation, and being guided to provide new k...","PeriodicalId":208962,"journal":{"name":"Int. J. Hum. Comput. Interact.","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131928096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：