A comparative study of the cascade-correlation architecture in pattern recognition applications
نویسندگان
چکیده
C o m p a ra t iv e S tu d y of th e C a s c a d e-C o r re la t io n A rc h ite c tu re in P a t te r n R e c o g n itio n A p p lic a tio n s Abstract In this work, an experimental evaluation of the cascade-correlation architecture is carried out in different bench-marking pattern recognition problems. An extensive experimental framework is developed to establish a comparison between the cascade-correlation network (CASCOR) and the more traditional multilayer perceptron (MLP) and radial basis function models (RBF). The different network conngurations are evaluated with respect to generalization performance in three practical real-world tasks: the diagnosis of coronary diseases (heart), the credit screening problem (card) and the recognition of handwritten characters. It is also considered the issue of catastrophic forgetting in MLP and CASCOR models. In addition to some clear potential advantages observed in the cascade-correlation network such as the on-learning deenition of the number of hidden units, the practical satisfactory results obtained suggest that the CASCOR model may represent in some situations an alternative to other traditional models such as the MLP and RBF networks.
منابع مشابه
Recognition of The Structure of Iranian Mosques in Comparison with Other Mosques of the Islamic World Based on The Concept of Perfectionism (Monotheism) In The Chalipa Symbol
The ancient Chalipa pattern in architecture is one of the patterns that have been considered as the main symbol of pre-Islamic Iranian architecture. Today, decoding different meanings of this symbol in the mosques as the base model, which is the source of Iranian and Islamic architecture, has been neglected. The present research is constantly attempting to compare the Iranian mosques with mosqu...
متن کاملComparative Study on Statistical-Variation Tolerance Between Complementary Crossbar and Twin Crossbar of Binary Nano-scale Memristors for Pattern Recognition
This paper performs a comparative study on the statistical-variation tolerance between two crossbar architectures which are the complementary and twin architectures. In this comparative study, 10 greyscale images and 26 black-and-white alphabet characters are tested using the circuit simulator to compare the recognition rate with varying statistical variation and correlation parameters.As with ...
متن کاملA Comparative Study of Gender and Age Classification in Speech Signals
Accurate gender classification is useful in speech and speaker recognition as well as speech emotion classification, because a better performance has been reported when separate acoustic models are employed for males and females. Gender classification is also apparent in face recognition, video summarization, human-robot interaction, etc. Although gender classification is rather mature in a...
متن کاملComparative Study of Two Various Percent of CO Injection Effect to Cascade Methanol Synthesis Reactor in the Presence of Long-term Catalyst Deactivation
متن کامل
A New Statistical Approach for Recognizing and Classifying Patterns of Control Charts (RESEARCH NOTE)
Control chart pattern (CCP) recognition techniques are widely used to identify the potential process problems in modern industries. Recently, artificial neural network (ANN) –based techniques are very popular to recognize CCPs. However, finding the suitable architecture of an ANN-based CCP recognizer and its training process are time consuming and tedious. In addition, because of the black box ...
متن کامل