Bayesian Continual Learning for Cognitive Artificial Intelligence
Keywords:
Bayesian inference, Cognitive artificial intelligence, Continual learning, Human thinking, emotionAbstract
Currently, most research on artificial intelligence (AI) is focused on the AI that can make optimal decisions. The optimal AI systems aim to minimize the misclassification rate in classification and mean squared error in regression. As the research on AI that extends beyond human intelligence to emotion is progressing, the interests of cognitive AI that can imitate human thinking and emotion increase. So, we proposed a continual learning model to construct the cognitive AI. In this paper, we define cognitive AI as an extended concept to include not only optimal decision but also rational decision that mimics human emotions. Human learning follows a lifelong learning process in which human existing intelligence or knowledge is continuously updated by new experiences throughout life. So, we study on a continual learning method based on Bayesian inference with Markov Chain Monte Carlo for making cognitive AI. To verify the performance of the proposed method, we carry out simulation study and make experiments using machine learning data.
Downloads
References
J.L. Bermudez, Cognitive Science, An Introduction to the Science of the Mind, 2nd ed., Cambridge University Press, Cambridge, UK, 2014.
Z. Chen, B. Liu, Lifelong Machine Learning, 2nd ed., Morgan & Claypool Publishers, Williston, VT, 2018.
R. Kurzweil, The Singularity Is Near When Humans Transcend Biology, Penguin Books, New York, 2006.
R. Kurzweil, How to create a mind, Penguin Books, New York, 2013.
B. Lake, T. Ullman, J. Tenenbaum, S. Gershman, Building machines that learn and think like people. Behavioral and Brain Sciences, 2017, 40, 1-72.
Anusha, D. J. ., R. . Anandan, and P. V. . Krishna. “Modified Context Aware Middleware Architecture for Precision Agriculture”. International Journal on Recent and Innovation Trends in Computing and Communication, vol. 10, no. 7, July 2022, pp. 112-20, doi:10.17762/ijritcc.v10i7.5635.
G.I. Parisi, R. Kemker, J.L. Part, C. Kanan, S. Wermter, Continual lifelong learning with neural networks: A review. Neural Networks 2019, 113, 54-71.
S. Russell, P. Norvig, Artificial Intelligence: A Modern Approach, 3rd ed.; Pearson: Essex, UK, 2014.
I. Goodfellow, Y. Bengio, A. Courville, Deep Learning; MIT Press: Cambridge, MA, 2016.
D. Silver, A. Huang, C.J. Maddison, A. Guez, L. Sifre, G. Driessche, J. Schrittwieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, S. Dieleman, D. Grewe, J. Nham, N. Kalchbrenner, I. Sutskever, T. Lillicrap, M. Leach, K. Kavukcuoglu, T. Graepel, D. Hassabis, Mastering the game of Go with deep neural networks and tree search. Nature 2016, 529, 484-489.
S. Jun, Machines Imitating Human Thinking Using Bayesian Learning and Bootstrap. Symmetry 2021, 13, 389.
M.A. Boden, Mind as machine: A history of cognitive science; Oxford University Press: Oxford, UK, 2006.
J. Hernandez-Orallo, The Measure of All Minds, Cambridge University Press, Cambridge, UK, 2017.
A. Kangasrääsiö, J.P.P. Jokinen, A. Oulasvirta, A. Howes, S. Kaski, Parameter Inference for Computational Cognitive Models with Approximate Bayesian Computation. Cognitive Science 2019, 43(6), e12738.
Agarwal, D. A. . (2022). Advancing Privacy and Security of Internet of Things to Find Integrated Solutions. International Journal on Future Revolution in Computer Science &Amp; Communication Engineering, 8(2), 05–08. https://doi.org/10.17762/ijfrcsce.v8i2.2067
A.S. Ahmad, Brain inspired cognitive artificial intelligence for knowledge extraction and intelligent instrumentation system. Proceedings of International Symposium on Electronics and Smart Devices 2017, 352-356.
A.D.W. Sumari, A.S. Ahmad, Knowledge-growing system: The origin of the cognitive artificial intelligence. Proceedings of 6th International Conference on Electrical Engineering and Informatics 2017, 1-7.
C.O. Sereati, A.D.W. Sumari, T. Adiono, A.S. Ahmad, Towards cognitive artificial intelligence device: an intelligent processor based on human thinking emulation. Telkomnika 2020, 18(3), 1475-1482.
A.K. Sangaiah, H. Lu, Q. Hu, Cognitive Science and Artificial Intelligence for Human Cognition and Communication. IEEE Consumer Electronics Magazine 2020, 9(1), 72-73.
D. Kelley, M. Twyman, Biasing in an Independent Core Observer Model Artificial General Intelligence Cognitive Architecture. Procedia Computer Science 2020, 169, 535-541.
X. Han, Y. Dai, T. Gao, Y. Lin, Z. Liu, P. Li, M. Sun, J. Zhou, Continual Relation Learning via Episodic Memory Activation and Reconsolidation. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 2020, 6429–6440
J. Yoon, E. Yang, J. Lee, S.J. Hwang, Lifelong Learning with Dynamically Expandable Networks. Proceedings of International Conference on Learning Representations 2018, 1-11.
Ravita, R., & Rathi, S. (2022). Inductive Learning Approach in Job Recommendation. International Journal of Intelligent Systems and Applications in Engineering, 10(2), 242–251. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/1829
J. Kirkpatricka, R. Pascanua, N. Rabinowitza, J. Venessa, G. Desjardinsa, A.A. Rusua, K. Milana, J. Quana, T. Ramalhoa, A. Grabska-Barwinskaa, D. Hassabisa, C. Clopathb, D. Kumarana, R. Hadsella, Overcoming cata-strophic forgetting in neural networks. PNAS 2017, 114(13), 3521-3526.
A. Mallya, S. Lazebnik, Packnet: Adding multiple tasks to a single network by iterative pruning. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition 2018, 7765-7773.
A. Robins, Catastrophic forgetting, rehearsal and pseudo rehearsal. Connection Science 1995, 7, 123-146.
J. Serra, D. Suris, M. Miron, A. Karatzoglou, Overcoming Catastrophic Forgetting with Hard Attention to the Task. Proceedings of the 35th International Conference on Machine Learning 2018, 80, 4548-4557.
T. Hoya, Artificial Mind System Kernel Memory Approach; Springer: New York, 2005.
I. Lubashevsky, Physics of the Human Mind; Springer: Cham, Switzerland, 2017.
Z. Shi, Mind Computation; World Scientific Publishing: Singapore, 2017.
M. Minsky, The Society of Mind; Simon & Schuster Paperbacks: New York, 1985.
M. Minsky, The Emotion Machine, Simon & Schuster Paperbacks: New York, 2006.
Z. Shi, H. Hu, Z. Shi, A Bayesian computational cognitive model. Proceedings of the 3rd International Conference on Neural-Symbolic Learning and Reasoning 2007, 230, 46-51
A. Perfors, J.B. Tenenbaum, T.L. Griffiths, F. Xu, A tutorial introduction to Bayesian models of cognitive development. Cognition 2011, 120(3), 302-321.
T.L. Griffiths, C. Kemp, J.B. Tenenbaum, Bayesian models of cognition; Cambridge University Press: Cambridge, UK ,2008.
A. Gelman, J.B. Carlin, H.S. Stern, D.B. Dunson, A. Vehtari, D.B. Rubin, Bayesian Data Analysis, 3rd ed.; Chapman & Hall/CRC Press: Boca Raton, FL, 2003.
H.M. Koduvely, Learning Bayesian Models with R; Packt: Birmingham, UK, 2015.
André Sanches Fonseca Sobrinho. (2020). An Embedded Systems Remote Course. Journal of Online Engineering Education, 11(2), 01–07. Retrieved from http://onlineengineeringeducation.com/index.php/joee/article/view/39
S. Theodoridis, Machine Learning A Bayesian and Optimization Perspective; Elsevier: London UK, 2015.
UC Irvine Machine Learning Repository. Available online: https://archive.ics.uci.edu/ml/ (accessed on 15 January 2021).
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
