感知计算、逻辑和自动机的基础
A Foundation to Perception Computing, Logic and Automata
摘要:
在这份报告中,介绍了一种新的智力和学习方法,这种方法是基于我们所说的“感知逻辑”。在此基础上,引入了计算机制和自动机。给出了感知信息的多分辨分析,其中学习至多在O(log(N))个历元内完成,其中N是样本数,并且保证收敛。这种方法结合了计算模型的优点,在这个意义上,他们是结构化的,数学定义良好,软计算方法的适应性,除了连续性和实时响应的动态系统。
英文摘要:
In this report, a novel approach to intelligence and learning is introduced, this approach is based on what we call 'perception logic'. Based on this logic, a computing mechanism and automata are introduced. Multi-resolution analysis of perceptual information is given, in which learning is accomplished in at most O(log(N))epochs, where N is the number of samples, and the convergence is guarnteed. This approach combines the favors of computational modeles in the sense that they are structured and mathematically well-defined, and the adaptivity of soft computing approaches, in addition to the continuity and real-time response of dynamical systems.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。