In many applications, desired system behavior is partially represented by data sets. In control systems, these data sets may represent operational states. In decision support systems and data analysis applications, these data sets may represent sample cases. The NeuroFuzzy Module allows for these data sets to be used for automated fuzzy logic system generation with any fuzzyTECH Edition.
Both generation of membership functions and fuzzy logic rules is supported, as well as automatic optimization towards the data sets.
Discussing the respective strengths and weaknesses of fuzzy logic and neural net technology, a simple comparison indicates that the strongest benefit of a neural net is that it can automatically learn from sample data. However, a neural net remains a black box, thus manual modification and verification of a trained net is not possible in a direct way.
This is where fuzzy logic excels: In a fuzzy logic system, any component is defined as close as possible to human intuition, making it very easy to manually modify and verify a designed system. However, fuzzy logic systems can not automatically learn from sample data.
This is where NeuroFuzzy provides "the best of both worlds". Take the explicit representation of knowledge in linguistic variables and rules from fuzzy logic and add the learning approach used with neural nets. Our NeuroFuzzy Module uses a modified Error-BackPropagation (EBP) algorithm to train rules and membership functions of a fuzzy logic system. The EBP is widely used in neural network applications and has been adapted by INFORM to the specific needs of training a fuzzy logic system.
The NeuroFuzzy Module
The NeuroFuzzy Module integrates completely with fuzzyTECH. At any time during a fuzzy logic design, you can use the NeuroFuzzy Module to generate or optimize part or an entire fuzzy logic system. After the NeuroFuzzy training, you can "see" explicitly which new rules have been generated or which rules have been dropped by the training. You also see, if and how the training process has adapted the membership functions. Thus, the result of a NeuroFuzzy training is no black box but remains transparent and can further be verified and modified manually.
Even during training, all modifications of the NeuroFuzzy Module can be made visible. Thus, you "see" how the NeuroFuzzy Module changes rules and membership functions to adapt the system behavior according to the sample data. The best way to understand how the NeuroFuzzy Module can assist your design, is to experience it yourself.
The NeuroFuzzy Module can also be used to optimize existing fuzzy logic systems. Starting with an existing fuzzy logic system, the NeuroFuzzy Module interactively tunes rule weights and membership function definitions so that the system converges to the behavior represented by the data sets. For this optimization process, rules and membership functions may be locked or opened for learning. Any fuzzy logic system generated by the NeuroFuzzy Module can be optimized manually and verified. User-defined training strategies can be integrated as DLLs using the NeuroFuzzy Module's open interface
Great post with lots of imoartpnt stuff. http://tdpvgtxvc.com [url=http://nmefbszmso.com]nmefbszmso[/url] [link=http://iqxngtiruxv.com]iqxngtiruxv[/link]
提问人： Rajkamal 发布时间： 2014/2/1 15:43:58
cialis This is getting a bit more stevbcuije, but I much prefer the Zune Marketplace. The interface is colorful, has more flair, and some cool features like Mixview' that let you quickly see related albums, songs, or other users related to what you're lis