Second Differentials in Arbitrary Feed-Forward Neural Networks
نویسنده
چکیده
We extend here a general mathematical model for feed-forward neural networks. Such a network is represented as a vectorial function f of two variables, x (the input of the network) and w (the weight vector). We have already shown that the differential of f can be computed with an extended back-propagation algorithm as well as with a direct method. In this paper, we show that the second differentials of f can also be computed with several different algorithms. Evaluating the theoretical complexities of these methods allow to choose the fastest algorithm for a particular architecture. This will allow us to handle arbitrary feed-forward neural network learning with the help of recent training and analysis techniques based on the Hessian matrix of the error.
منابع مشابه
Handwritten Character Recognition using Modified Gradient Descent Technique of Neural Networks and Representation of Conjugate Descent for Training Patterns
The purpose of this study is to analyze the performance of Back propagation algorithm with changing training patterns and the second momentum term in feed forward neural networks. This analysis is conducted on 250 different words of three small letters from the English alphabet. These words are presented to two vertical segmentation programs which are designed in MATLAB and based on portions (1...
متن کاملEffect of sound classification by neural networks in the recognition of human hearing
In this paper, we focus on two basic issues: (a) the classification of sound by neural networks based on frequency and sound intensity parameters (b) evaluating the health of different human ears as compared to of those a healthy person. Sound classification by a specific feed forward neural network with two inputs as frequency and sound intensity and two hidden layers is proposed. This process...
متن کاملPREDICTION OF COMPRESSIVE STRENGTH AND DURABILITY OF HIGH PERFORMANCE CONCRETE BY ARTIFICIAL NEURAL NETWORKS
Neural networks have recently been widely used to model some of the human activities in many areas of civil engineering applications. In the present paper, artificial neural networks (ANN) for predicting compressive strength of cubes and durability of concrete containing metakaolin with fly ash and silica fume with fly ash are developed at the age of 3, 7, 28, 56 and 90 days. For building these...
متن کاملModeling of Resilient Modulus of Asphalt Concrete Containing Reclaimed Asphalt Pavement using Feed-Forward and Generalized Regression Neural Networks
Reclaimed asphalt pavement (RAP) is one of the waste materials that highway agencies promote to use in new construction or rehabilitation of highways pavement. Since the use of RAP can affect the resilient modulus and other structural properties of flexible pavement layers, this paper aims to employ two different artificial neural network (ANN) models for modeling and evaluating the effects of ...
متن کامل