标题: | 具有处理模糊语言能力之类神经网路系统 A Neural Fuzzy System with Linguistic Teaching Signals |
作者: | 吕雅菁 Ya-Ching Lu 林进灯 Dr. Chin-Teng Lin 资讯科学与工程研究所 |
关键字: | 模糊集合; 类神经网路; 评论性学习; 倒传递法则; 语言性资料;知识库压缩;Fuzzy Set; Neural Network; Reinforcement learning; inguistic Data |
公开日期: | 1993 |
摘要: | 本篇论文提出一具有处理模糊语言之类神经网路系统。我们使用α- level sets形式的模糊集合(fuzzy number)来表示一个语言性质的资料 (linguistic data)。本论文首先提出一个五层的类神经网路架构,这个 架构能处理数值性(numerical)的输入以及模糊语言的输入,而且针对不 同性质的应用,产生所需要的数值性的输出或模糊的输出。这个架构并不 需要太多的空间及记算时间,而能够表示任何形态的模糊集合。至于学习 方式,我们讨论了有指导性 (supervised) 的学习方式及评论性质 (reinforcement learning) 的学习方式。对于有指导性的学习方式,一 个重要的应用–知识库压缩 (rule base concentration) 被展示。至于 评论性质的学习方式,我们强调评论讯息 (reinforcement signal) 是一 种模糊资料,而不像传统的方式只使用数字来表示。而且针对两种不同性 质的问题,single-step及 multi- step 的预测方法分别地被提出。常见 的倒单摆 (cart-pole balancing)问题被实际地模拟来显示我们所提之系 统的功效。 A neural fuzzy system with linguistic teaching signals is proposed in this thesis. We use fuzzy numbers based on α-level sets to represent linguistic information. At first, we propose a five-layered neural network which can process numerical information as well as linguistic information. Moreover, the inputs and outputs of this five-layered connectionist architecture can be a hybrid of fuzzy numbers an numerical numbers. The important characteristics of the proposed model are that the network weights can be fuzzy numbers of any shaped and the performance of this model is superior to several other methods both in learning speed and memory requirement. Two kinds of learning schemes are discussed: supervised learning and reinforcement learning. With supervised learning, the proposed model can be used for rule base concentration to reduce the number of rules in knowledge base. For reinforcement learning, we consider that the reinforcement signal from environment is linguistic information such as "good" , "very good", or "bad". We discuss two kinds of reinforcement learning learning problems:single-step prediction problems and multi- step prediction problems. Simulation results of the cart- pole balancing problem are presented to illustrate the performance and applicability of the proposed reinforcement system. |
URI: | http://140.113.39.130/cdrfb3/record/nctu/#NT820394039 http://hdl.handle.net/11536/57938 |
显示于类别: | Thesis |