THE ROLES OF PROGRAM, DATA AND FILTER IN ARTIFICIAL INTELLIGENCE

Chien-Chang Yen

《Journal of Data Analysis》 17卷4期特刊 (2022/12) Pp. 33-47

https://doi.org/10.6338/JDA.202212/SP_17(4).0004

摘要

Artificial intelligence (AI) can be assistants of human or mimic human's behavior, like self-driving cars, robotic arms, smart platform for long-term care, etc. Its powerful ability induces people's concerns on several fields, computer science, robotic machines, financial markets, philosophy, and religion. Moreover, AI may or may not have the mind of a human or social behavior of human in future. This article tries to explain AI from the deep learning in the sense of weak AI through the three components in machine learning, program, data and filters. Meanwhile, this background knowledge provides the opportunity to probe the connection between the week AI and strong AI.

關鍵字

AI ； program ； data ； filter

參考文獻

[CCYen2009] Chien-Chang Yen, Wei-Chang Shann, Chen-Tung Yen, Meng-Li Tasi, Spike sorting by a minimax reduced feature set based on finite differences, J Physiol Sci (2009) 59: 143-147. DOI 10.1007/s12576-008-0010-x

[Elman1990] Elman, Jeffrey L. (1990). "Finding Structure in Time". Cognitive Science. 14 (2): 179–211. doi:10.1016/0364-0213(90)90002-E

[Jordan1997] Jordan, Michael I. (1997-01-01). "Serial Order: A Parallel Distributed Processing Approach". Neural-Network Models of Cognition -Biobehavioral Foundations. Advances in Psychology. Neural-Network Models of Cognition. Vol. 121. pp. 471–495. doi:10.1016/s0166-4115(97)80111-2. ISBN 9780444819314.

[Schmidhuber2015] Schmidhuber, Jürgen (January 2015). "Deep Learning in Neural Networks: An Overview". Neural Networks. 61: 85-117. arXiv:1404.7828. doi:10.1016/j.neunet.2014.09.003. PMID 25462637. S2C ID 11715509.

[Quaglio2018] Pietro Quaglio, Vahid Rostami, Emiliano Torre, Sonja Grun (2018), “Methods for identification of spike patterns in massively parallel spike trains”, Biological Cybernetics, 112:57-80 ( https://doi.org/10.1007/s00422-018-0755-0)