A "neural" network model that supports realtime learning of temporal relationships in complex engineering domains
Article Abstract:
Difficulties in developing, maintaining, and validating knowledge base have motivated an increasing interest in adaptive systems. However, the symbolic paradigm has proven resistant to learning in environments that are dynamic or noisy. This report documents a simulation-based research program that demonstrates the utility of a modified connectionist memory unit as the basis for a robust reinforcement model that learns in such environments. This learning model generates effective rule-based behavior from a qualitative, goal-based architecture that further supports the development of secondary goals, or mental models, derived from experiences in these complex domains. (Reprinted with permission of the publisher.)
Publication Name: SIMULATION
Subject: Engineering and manufacturing industries
ISSN: 0037-5497
Year: 1992
User Contributions:
Comment about this article or add new information about this topic:
University-Industry Research Relationships
Article Abstract:
A survey was conducted to identify the most significant factors impeding the university-industry research relationship. A questionnaire was submitted to research management in the industry and research personnel at the universities. The biggest impediment identified in the survey is the university's concern involving the right to publish and the industry's need to protect proprietary information. Duplication of research efforts, industry's short term profits orientation, and conflict of interest were some of the other concerns. A significant number of those questioned thought that the university-industry research relationship has improved since 1977.
Publication Name: Research Management
Subject: Engineering and manufacturing industries
ISSN: 0034-5334
Year: 1984
User Contributions:
Comment about this article or add new information about this topic:
Network more effectively with this checklist
Article Abstract:
Networking is a complicated process that requires adequate planning and dedication on the part of the networker. Thus, it is important for networkers to identify the different factors that affect the networking process. These include the choice of the right networking activities and the development and use of conversation skills. Several techniques for effective networking are presented.
Publication Name: Research-Technology Management
Subject: Engineering and manufacturing industries
ISSN: 0895-6308
Year: 1995
User Contributions:
Comment about this article or add new information about this topic:
- Abstracts: The next 25 years: the future of the construction industry. What you can do to improve engineering education
- Abstracts: Aftermath of battle: using new applications in clearing unexploded ordnance. Durable LVDTs ideal in new gage applications
- Abstracts: Acoustic liner withstands high temperature. An environment where eagles soar. New glass curbs cracks
- Abstracts: A model for the management of building evacuation. Building trust is an art. Building clever
- Abstracts: Your word is my command. Hawker has last word in ELV switching. 500-Word Voice Card for IBM PC-XT