Home About us Contact
|
Home About us Contact | ||
|
|
||
Better Generalization (good + generalization)
Selected AbstractsA hybrid Bayesian back-propagation neural network approach to multivariate modellingINTERNATIONAL JOURNAL FOR NUMERICAL AND ANALYTICAL METHODS IN GEOMECHANICS, Issue 8 2003C. G. Chua Abstract There is growing interest in the use of back-propagation neural networks to model non-linear multivariate problems in geotehnical engineering. To overcome the shortcomings of the conventional back-propagation neural network, such as overfitting, where the neural network learns the spurious details and noise in the training examples, a hybrid back-propagation algorithm has been developed. The method utilizes the genetic algorithms search technique and the Bayesian neural network methodology. The genetic algorithms enhance the stochastic search to locate the global minima for the neural network model. The Bayesian inference procedures essentially provide better generalization and a statistical approach to deal with data uncertainty in comparison with the conventional back-propagation. The uncertainty of data can be indicated using error bars. Two examples are presented to demonstrate the convergence and generalization capabilities of this hybrid algorithm. Copyright © 2003 John Wiley & Sons, Ltd. [source] The Role of Diminutives in the Acquisition of Russian Gender: Can Elements of Child-Directed Speech Aid in Learning Morphology?LANGUAGE LEARNING, Issue 2 2001Vera Kempe Diminutives are a pervasive feature of child-directed speech (CDS) in Russian. Their frequent use might be beneficial for gender acquisition because it eliminates nontransparent morphophonological marking. To examine the effect of diminutives on gender learning, adult native speakers of English were taught Russian nouns, with half of the participants trained on diminutive nouns and half on the nondiminutive base forms. Over four sessions, participants learned to use adjectives that had to agree in gender with nouns. Learners were then tested on various types of novel nouns. The diminutive training group demonstrated better learning of noun gender, and better generalization to novel forms, indicating that regularization of gender marking through diminutives promotes the extraction of morphophonological regularities. [source] Multiple neural networks modeling techniques in process control: a reviewASIA-PACIFIC JOURNAL OF CHEMICAL ENGINEERING, Issue 4 2009Zainal Ahmad Abstract This paper reviews new techniques to improve neural network model robustness for nonlinear process modeling and control. The focus is on multiple neural networks. Single neural networks have been dominating the neural network ,world'. Despite many advantages that have been mentioned in the literature, some problems that can deteriorate neural network performance such as lack of generalization have been bothering researchers. Driven by this, neural network ,world' evolves and converges toward better representations of the modeled functions that can lead to better generalization and manages to sweep away all the glitches that have shadowed neural network applications. This evolution has lead to a new approach in applying neural networks that is called as multiple neural networks. Just recently, multiple neural networks have been broadly used in numerous applications since their performance is literally better than that of those using single neural networks in representing nonlinear systems. Copyright © 2009 Curtin University of Technology and John Wiley & Sons, Ltd. [source] PREDICTION OF MECHANICAL PROPERTIES OF CUMIN SEED USING ARTIFICIAL NEURAL NETWORKSJOURNAL OF TEXTURE STUDIES, Issue 1 2010M.H. SAIEDIRAD ABSTRACT In this paper, two artificial neural networks (ANNs) are applied to acquire the relationship between the mechanical properties and moisture content of cumin seed, using the data of quasi-static loading test. In establishing these relationship, the moisture content, seed size, loading rate and seed orientation were taken as the inputs of both models. The force and energy required for fracturing of cumin seed, under quasi-static loading were taken as the outputs of two models. The activation function in the output layer of models obeyed a linear output, whereas the activation function in the hidden layers were in the form of a sigmoid function. Adjusting ANN parameters such as learning rate and number of neurons and hidden layers affected the accuracy of force and energy prediction. Comparison of the predicted and experimented data showed that the ANN models used to predict the relationships of mechanical properties of cumin seed have a good learning precision and good generalization, because the root mean square errors of the predicated data by ANNs were rather low (4.6 and 7.7% for the force and energy, respectively). PRACTICAL APPLICATIONS Cumin seed is generally used as a food additive in the form of powder for imparting flavor to different food preparations and for a variety of medicinal properties. Physical properties of cumin seeds are essential for the design of equipment for handling, harvesting, aeration, drying, storing, grinding and processing. For powder preparation especially the fracture behavior of the seeds are essential. These properties are affected by numerous factors such as size, form and moisture content of the grain and deformation speed. A neural network model was developed that can be used to predict the relationships of mechanical properties. Artificial neural network models are powerful empirical models approach, which can be compared with mathematical models. [source] | ||||||||||