Bi-radial Transfer Functions
نویسنده
چکیده
The most common transfer functions in neural networks are of the sigmoidal type. In this article other transfer functions are considered. Advantages of simple gaussians, giving hyperelliptical densities, and gaussian bar functions (sums of one-dimensional gaussians) are discussed. Bi-radial functions are formed from products of two sigmoids. Product of M bi-radial functions in N -dimensional parameter space give arbitrarily shaped densities offering great flexibility. Extensions of bi-radial functions are proposed. Bi-radial functions can be used as transfer functions in many neural networks, such as RBF, RAN or FSM systems.
منابع مشابه
Approximation and classification with RBF-type Neural Networks using flexible local and semi-local transfer functions
Structure of incremental neural network (IncNet) is controlled by growing and pruning to match the complexity of training data. Extended Kalman Filter algorithm and its fast version is used as learning algorithm. Bi-radial transfer functions, more flexible than other functions commonly used in artificial neural networks, are used. The latest improvement added is the ability to rotate the contou...
متن کاملApproximation and classification with RBF-type Neural Networks using flexible local and semi-local transfer functions1
Structure of incremental neural network (IncNet) is controlled by growing and pruning to match the complexity of training data. Extended Kalman Filter algorithm and its fast version is used as learning algorithm. Bi-radial transfer functions, more flexible than other functions commonly used in artificial neural networks, are used. The latest improvement added is the ability to rotate the contou...
متن کاملApproximation and Classification in Medicine with IncNet Neural Networks
Structure of incremental neural network (IncNet) is controlled by growing and pruning to match the complexity of training data. Extended Kalman Filter algorithm and its fast version is used as learning algorithm. Bi-central transfer functions, more flexible than other functions commonly used in artificial neural networks, are used. The latest improvement added is the ability to rotate the conto...
متن کاملApproximation and Classification in Medicine with IncNet Neural Networks1
Structure of incremental neural network (IncNet) is controlled by growing and pruning to match the complexity of training data. Extended Kalman Filter algorithm and its fast version is used as learning algorithm. Bi-central transfer functions, more flexible than other functions commonly used in artificial neural networks, are used. The latest improvement added is the ability to rotate the conto...
متن کاملCertain subclasses of bi-univalent functions associated with the Aghalary-Ebadian-Wang operator
In this paper, we introduce and investigate two new subclasses of the functions class $ Sigma $ of bi-univalent functions defined in the open unit disk, which are associated with the Aghalary-Ebadian-Wang operator. We estimate the coefficients $|a_{2} |$ and $|a_{3} |$ for functions in these new subclasses. Several consequences of the result are also pointed out.
متن کامل