ABSTRACT
Performance of a cognitive personal assistant, RADAR, consisting of multiple machine learning components, natural language processing, and optimization was examined with a test explicitly developed to measure the impact of integrated machine learning when used by a human user in a real world setting. Three conditions (conventional tools, Radar without learning, and Radar with learning) were evaluated in a large-scale, between-subjects study. The study revealed that integrated machine learning does produce a positive impact on overall performance. This paper also discusses how specific machine learning components contributed to human-system performance.
- Steinfeld, A., Bennett, R., Cunningham, K., Lahut, M., Quinones, P.-A., Wexler, D., Siewiorek, D., Cohen, P., Fitzgerald, J., Hansson, O., Hayes, J., Pool, M., and Drummond, M., The RADAR Test Methodology: Evaluating a Multi-Task Machine Learning System with Humans in the Loop. 2006, Carnegie Mellon University, School of Computer Science: Pittsburgh, PA. http://reports-archive.adm.cs.cmu.edu/anon/2006/abs tracts/06-125.htmlGoogle Scholar
- Clymer, J. R. Simulation of a vehicle traffic control network using a fuzzy classifier system. In Proc. of the IEEE Simulation Symposium. 2002. Google ScholarDigital Library
- Clymer, J. R. and Harrsion, V. Simulation of air traffic control at a VFR airport using OpEMCSS. In Proc. IEEE Digital Avionics Systems Conference. 2002.Google ScholarCross Ref
- Zhang, L., Samaras, D., Tomasi, D., Volkow, N., and Goldstein, R. Machine learning for clinical diagnosis from functional magnetic resonance imaging. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2005. Google ScholarDigital Library
- Hu, Y., Li, H., Cao, Y., Meyerzon, D., and Zheng, Q. Automatic extraction of titles from general documents using machine learning. In Proc. of ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL). 2005. Google ScholarDigital Library
- Allen, J., Chambers, N., Ferguson, G., Galescu, L., Jung, H., Swift, M., and Taysom, W. PLOW: A Collaborative Task Learning Agent. In Proc. Conference on Artificial Intelligence (AAAI). 2007. Vancouver, Canada. Google ScholarDigital Library
- Schrag, R., Pool, M., Chaudhri, V., Kahlert, R., Powers, J., Cohen, P., Fitzgerald, J., and Mishra, S. Experimental evaluation of subject matter expert-oriented knowledge base authoring tools. In Proc. NIST Performance Metrics for Intelligent Systems Workshop. 2002. http://www.iet.com/Projects/RKF/PerMIS02.docGoogle Scholar
- Shen, J., Li, L., Dietterich, T. G., and Herlocker, J. L. A hybrid learning system for recognizing user tasks from desktop activities and email messages. In Proc. International Conference on Intelligent User Interfaces (IUI). 2006. Google ScholarDigital Library
- Yoo, J., Gervasio, M., and Langley, P. An adaptive stock tracker for personalized trading advice. In Proc. International Conference on Intelligent User Interfaces (IUI). 2003. Google ScholarDigital Library
- Airspace: Tools for evaluating complex systems, machine language, and complex tasks. http://www.cs.cmu.edu/~airspaceGoogle Scholar
- Steinfeld, A., Quinones, P.-A., Zimmerman, J., Bennett, S. R., and Siewiorek, D. Survey measures for evaluation of cognitive assistants. In Proc. NIST Performance Metrics for Intelligent Systems Workshop (PerMIS). 2007. Google ScholarDigital Library
Recommendations
Machine Learning Task as a Diclique Extracting Task
FSKD '09: Proceedings of the 2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery - Volume 01As we know there exist several approaches and algorithms for data mining and machine learning task solution, for example, decision tree learning, artificial neural networks, Bayesian learning, instance-based learning, genetic algorithms, etc. They are ...
Machine learning task as a diclique extracting task
FSKD'09: Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 1As we know there exist several approaches and algorithms for data mining and machine learning task solution, for example, decision tree learning, artificial neural networks, Bayesian learning, instance-based learning, genetic algorithms, etc. They are ...
Machine Learning: The State of the Art
The two fundamental problems in machine learning (ML) are statistical analysis and algorithm design. The former tells us the principles of the mathematical models that we establish from the observation data. The latter defines the conditions on which ...
Comments