One-to-many mappings represented on feed-forward networks
نویسندگان
چکیده
Multiplayer perceptrons or feed-forward networks are generally trained to represent functions or many-to-one (m-o) mappings. This creates a problem if the training data exhibits the property of many-to-many or almost many-many valued-ness because the model, which generated the data, was many-to-many. Therefore in this paper a modified feed-forward network and training algorithm is considered to represent a multi-valued mappings. The solution consists of adding another input to the standard feed-forward network and of modifying the training algorithm. This additional input will generally have no training values provided and an amended training algorithm is used to find its values. The modified feed-forward network and training method has been successfully applied both in representing the mapping implied by data generated by multivalued functions and in representing the mapping implied by data obtained from benchmark databases.
منابع مشابه
The Choice Problem: Neural Network Learning, Generalization, and Geometry
We study the learning and generalization capacity of layered feed-forward neural networks in the context of mappings of arbitrarily long bit strings into one of three ordered outputs. Many signal-processing applications reduce to this problem. We use the back-propagation learning algorithm to train the network. We describe these mappings in terms of collections of linear partitions of the input...
متن کاملStoring many-to-many mappings on a feed-forward neural network using fuzzy sets
Feed-forward networks are generally trained to represent functions or many-toone (m-o) mappings. In this paper however a feed-forward network with modified training algorithm is considered to represent multi-valued or one-tomany (o-m) mappings. The o-m mapping is viewed as an m-o mapping where the values corresponding to a value of the independent variable are sets. Thus the problem of represen...
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 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 کاملTraining a feed-forward network with incomplete data due to missing input variables
Data available for training a neural network may be deficient not only in quantity of data but entire independent variables with their data may be missing such as is often the situation for software engineering data. This may cause the relation based on the available data to exhibit the property of one-to-many (o-m) valuedness or almost o-m valuedness. Multiplayer perceptrons or feed-forward ne...
متن کامل