跳至主要内容

Motivation Learning in Mind Model CAM

Read  full  paper  at:
http://www.scirp.org/journal/PaperInformation.aspx?PaperID=53181#.VLcb0snQrzE

Author(s)  
 
ABSTRACT
Motivation learning aims to create abstract motivations and related goals. It is one of the high-level cognitive functions in Consciousness And Memory model (CAM). This paper proposes a new motivation learning algorithm which allows an agent to create motivations or goals based on introspective process. The simulation of cyborg rat maze search shows that the motivation learning algorithm can adapt agents’ behavior in response to dynamic environment.
 
Cite this paper
Shi, Z. , Ma, G. , Yang, X. and Lu, C. (2015) Motivation Learning in Mind Model CAM. International Journal of Intelligence Science, 5, 63-71. doi: 10.4236/ijis.2015.52006.
 
References
[1]Shi, Z.Z., Wang, X.F., Chen, L.M. and Zhang, Z.X. (2010) A Mind Model CAM—Consciousness and Memory Model. Proceedings of 7th International Conference on Cognitive Science, Beijing, 17-20 August 2010, 226-227.
 
[2]Mook, D.G. (1987) Motivation: The Organization of Action. W. W. Norton and Company, Inc., New York.
 
[3]Maslow, A.H. (1943) A Theory of Human Motivation. Psychological Review, 50, 370-396.
http://dx.doi.org/10.1037/h0054346
 
[4]Green, R.G., Beatty, W.W. and Arkin, R.M. (1984) Human Motivation: Physiological, Behavioral and Social Approaches. Allyn and Bacon, Inc., Boston.
 
[5]Merrick, K. (2007) Modelling Motivation for Experience-Based Attention Focus in Reinforcement Learning. Ph.D. Thesis, The University of Sydney, Sydney.
 
[6]Starzyk, J.A. (2012) Motivated Learning for Computational Intelligence. In: Information Resources Management Association, Ed., Machine Learning: Concepts, Methodologies, Tools and Applications (3 Volumes), IGI Global, Hershey, 120-146.
 
[7]Oudeyer, P.-Y., Kaplan, F. and Hafner, V. (2007) Intrinsic Motivation Systems for Autonomous Mental Development. IEEE Transactions on Evolutionary Computation, 11, 265-286.
http://dx.doi.org/10.1109/TEVC.2006.890271
 
[8]Berlyne, D.E. (1960) Conflict, Arousal and Curiosity. McGraw-Hill, New York.
http://dx.doi.org/10.1037/11164-000
 
[9]Schmidhuber, J. (1991) Curious Model—Building Control Systems. Proceedings of the International Joint Conference on Neural Networks, Singapore City, 18-21 November 1991, 1458-1463.
 
[10]Markou, M. and Singh, S. (2003) Novelty Detection: A Review—Part 1: Statistical Approaches. Signal Processing, 83, 2481-2497. http://dx.doi.org/10.1016/j.sigpro.2003.07.018
 
[11]Markou, M. and Singh, S. (2003) Novelty Detection: A Review—Part 2: Neural Network Based Approaches. Signal Processing, 83, 2499-2521. http://dx.doi.org/10.1016/j.sigpro.2003.07.019
 
[12]Shi, Z.Z. (2011) Intelligence Science. World Scientific, Singapore City.
 
[13]Cox, M. (2005) Metacognition in Computation: A Selected Research Review. Artificial Intelligence, 169, 104-141. http://dx.doi.org/10.1016/j.artint.2005.10.009
 
[14]Laird, J.E., Newell, A. and Rosenbloom, P.S. (1987) SOAR: An Architecture for General Intelligence. Artificial Intelligence, 33, 1-64. http://dx.doi.org/10.1016/0004-3702(87)90050-6
 
[15]Birnbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B. and Pryor, L. (1991) A Model-Based Approach to the Construction of Adaptive Case-Based Planning Systems. Proceedings of the DARPA Case-Based Reasoning Workshop, Morgan Kaufmann, San Mateo, 215-224.
 
[16]Cox, M.T. and Ram, A. (1999) Introspective Multistrategy Learning: On the Construction of Learning Strategies. Artificial Intelligence, 112, 1-55. http://dx.doi.org/10.1016/S0004-3702(99)00047-8
 
[17]Leake, D.B. and Wilson, M. (2008) Extending Introspective Learning from Self-Models. In: Cox, M.T. and Raja, A., Eds., Metareasoning: Thinking about Thinking, AAAI Press, Palo Alto, 143-146.
 
[18]Eriksen, C. and St James, J. (1986) Visual Attention within and around the Field of Focal Attention: A Zoom Lens Model. Perception & Psychophysics, 40, 225-240. http://dx.doi.org/10.3758/BF03211502
 
[19]Baddeley, A. (2000) The Episodic Buffer: A New Component of Working Memory? Trends in Cognitive Sciences, 4, 417-423. http://dx.doi.org/10.1016/S1364-6613(00)01538-2
 
[20]Shi, Z.Z., Wang, X.F. and Yue, J.P. (2011) Cognitive Cycle in Mind Model CAM. International Journal of Intelligence Science, 1, 25-34. http://dx.doi.org/10.4236/ijis.2011.12004
 
[21]Shi, Z.Z., Zhang, J.H., Yue, J.P. and Qi, B.Y. (2013) A Motivational System for Mind Model CAM. AAAI Symposium on Integrated Cognition, Virginia, 15-17 November 2013, 79-86.
 
[22]Saunders, R. and Gero, J.S. (2002) Curious Agents and Situated Design Evaluations. In: Gero, J.S. and Brazier, F.M.T., Eds., Agents in Design, Key Centre of Design Computing and Cognition, University of Sydney, Sydney, 133-149.
 
[23]Li, Q.Y., Shi, J. and Shi, Z.Z. (2005) A Model of Attention-Guided Visual Sparse Coding. Proceedings of IEEE International Conference on Cognitive Informatics, Irvine, 8-10 August 2005, 120-125.          eww150115lx
标签：

评论

发表评论

此博客中的热门博文

A Comparison of Methods Used to Determine the Oleic/Linoleic Acid Ratio in Cultivated Peanut (Arachis hypogaea L.)

Cultivated peanut ( Arachis hypogaea L.) is an important oil and food crop. It is also a cheap source of protein, a good source of essential vitamins and minerals, and a component of many food products. The fatty acid composition of peanuts has become increasingly important with the realization that oleic acid content significantly affects the development of rancidity. And oil content of peanuts significantly affects flavor and shelf-life. Early generation screening of breeding lines for high oleic acid content greatly increases the efficiency of developing new peanut varieties. The objective of this study was to compare the accuracy of methods used to classify individual peanut seed as high oleic or not high oleic. Three hundred and seventy-four (374) seeds, spanning twenty-three (23) genotypes varying in oil composition (i.e. high oleic (H) or normal/not high oleic (NH) inclusive of all four peanut market-types (runner, Spanish, Valencia and Virginia), were individually tested ...
发表评论
阅读全文

Location Optimization of a Coal Power Plant to Balance Costs against Plant’s Emission Exposure

Fuel and its delivery cost comprise the biggest expense in coal power plant operations. Delivery of electricity from generation to consumers requires investment in power lines and transmission grids. Placing a coal power plant or multiple power plants near dense population centers can lower transmission costs. If a coalmine is nearby, transportation costs can also be reduced. However, emissions from coal plants play a key role in worsening health crises in many countries. And coal upon combustion produces CO 2 , SO 2 , NO x , CO, Metallic and Particle Matter (PM10 & PM2.5). The presence of these chemical compounds in the atmosphere in close vicinity to humans, livestock, and agriculture carries detrimental health consequences. The goal of the research was to develop a methodology to minimize the public’s exposure to harmful emissions from coal power plants while maintaining minimal operational costs related to electric distribution losses and coal logistics. The objective was...
发表评论
阅读全文

Evaluation of the Safety and Efficacy of Continuous Use of a Home-Use High-Frequency Facial Treatment Appliance

At present, many home-use beauty devices are available in the market. In particular, many products developed for facial treatment use light, e.g., a flash lamp or a light-emitting diode (LED). In this study, the safety of 4 weeks’ continuous use of NEWA TM , a high-frequency facial treatment appliance, every alternate day at home was verified, and its efficacy was evaluated in Japanese individuals with healthy skin aged 30 years or older who complained of sagging of the facial skin.  Transepidermal water loss (TEWL), melanin levels, erythema levels, sebum secretion levels, skin color changes and wrinkle improvement in the facial skin were measured before the appliance began to be used (study baseline), at 2 and 4 weeks after it had begun to be used, and at 2 weeks after completion of the 4-week treatment period (6 weeks from the study baseline). In addition, data obtained by subjective evaluation by the subjects themselves on a visual analog scale (VAS) were also analyzed. Fur...
发表评论
阅读全文