Sensitivity Analysis for Selective Learning by Feedforward Neural Networks
نویسنده
چکیده
Research on improving the performance of feedforward neural networks has concentrated mostly on the optimal setting of initial weights and learning parameters, sophisticated optimization techniques, architecture optimization, and adaptive activation functions. An alternative approach is presented in this paper where the neural network dynamically selects training patterns from a candidate training set during training, using the network’s current attained knowledge about the target concept. Sensitivity analysis of the neural network output with respect to small input perturbations is used to quantify the informativeness of candidate patterns. Only the most informative patterns, which are those patterns closest to decision boundaries, are selected for training. Experimental results show a significant reduction in the training set size, without negatively influencing generalization performance and convergence characteristics. This approach to selective learning is then compared to an alternative where informativeness is measured as the magnitude in prediction error.
منابع مشابه
Numerical solution of fuzzy linear Fredholm integro-differential equation by \fuzzy neural network
In this paper, a novel hybrid method based on learning algorithmof fuzzy neural network and Newton-Cotesmethods with positive coefficient for the solution of linear Fredholm integro-differential equation of the second kindwith fuzzy initial value is presented. Here neural network isconsidered as a part of large field called neural computing orsoft computing. We propose alearning algorithm from ...
متن کاملNumerical solution of fuzzy differential equations under generalized differentiability by fuzzy neural network
In this paper, we interpret a fuzzy differential equation by using the strongly generalized differentiability concept. Utilizing the Generalized characterization Theorem. Then a novel hybrid method based on learning algorithm of fuzzy neural network for the solution of differential equation with fuzzy initial value is presented. Here neural network is considered as a part of large eld called ne...
متن کاملA Regularized Learning Method for Neural Networks Based on Sensitivity Analysis
The Sensitivity-Based Linear Learning Method (SBLLM) is a learning method for two-layer feedforward neural networks, based on sensitivity analysis, that calculates the weights by solving a system of linear equations. Therefore, there is an important saving in computational time which significantly enhances the behavior of this method compared to other learning algorithms. This paper introduces ...
متن کاملA new initialization method for neural networks using sensitivity analysis
The learning methods for feedforward neural networks find the network’s optimal parameters through a gradient descent mechanism starting from an initial state of the parameters. This initial state influences both in convergence speed and the error that finally is achieved. In this paper, we present a sensitivity analysis based initialization method for two-layer feedforward neural networks, whi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Fundam. Inform.
دوره 46 شماره
صفحات -
تاریخ انتشار 2001