作者: James C. Bezdek
DOI: 10.1007/978-3-642-58930-0_2
关键词: Evolutionary computation 、 Computational intelligence 、 Fuzzy logic 、 Expert system 、 Artificial intelligence 、 Rational expectations 、 Artificial neural network 、 Enthusiasm 、 Computer science 、 Robustness (computer science) 、 Hybrid system
摘要: Here is the abstract from my 1992 paper about Computational Intelligence (CI) [1]: This concerns relationship between neural-like computational networks, numerical pattern recognition and intelligence. Extensive research that proposes use of neural models for a wide variety applications has been conducted in past few years. Sometimes justification investigating potential nets (NNs) obvious. On other hand, current enthusiasm this approach also led to when apparent rationale their justified by what best described as “feeding frenzy”. In latter instance there at times concomitant lack concern many “side issues” connected with algorithms (e.g., complexity, convergence, stability, robustness performance validation) need attention before any model becomes part an operational system. These issues are examined view towards guessing how integrate exploit promise efforts aimed advancing art science its fielded systems next decade. A further purpose present characterize notions computational, artificial biological intelligence; hope careful discussion exhibit each these properties will serve guide rational expectations development or mimic “human behavior”.