Eecient Detection of Spurious Inputs for Improving the Robustness of Mlp Networks in Practical Applications Eecient Detection of Spurious Inputs for Improving the Robustness of Mlp Networks in Practical Applications

نویسندگان

  • G. C. Vasconcelos
  • M. C. Fairhurst
  • D. L. Bisset
چکیده

The problem of the rejection of patterns not belonging to identiied training classes is investigated with respect to multilayer perceptron networks (MLPs). The reason for the inherent unreliability of the standard MLP in this respect is explained and some mechanisms for the enhancement of its rejection performance are considered. Two network conngurations are presented as candidates for a more reliable structure and are compared to the so-called \negative training" approach. The rst connguration is an MLP which uses a Gaussian as its activation function and the second is an MLP with direct connections from the input to the output layer of the network. The networks are examined and evaluated both through the technique of network inversion and through practical experiments in a pattern classiication application. Finally, the model of radial basis function networks (RBFs) is also considered in this respect and its performance is compared to that attained with the other networks described.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

An investigation of feedforward neural networks with respect to the detection of spurious patterns

This thesis investigates feedforward neural networks in the context of classi cation tasks with respect to the detection of patterns that do not belong to the same categories of patterns used to train the network. This refers to the problem of the detection and/or rejection of spurious or novel patterns. In particular, the multilayer perceptron network (MLP) trained with the backpropagation alg...

متن کامل

A Bootstrap-like Rejection Mechanism for Multilayer Perceptron Networks

Multilayer perceptron networks (MLP) are investigated with respect to the problem of the detection of spurious patterns. A novel mechanism is proposed based on the ideas of boot-strapping that when incorporated into the standard MLP provides the network with the ability to continuously modifying its responses across the input space. The mechanism makes use of the outputs given by the network it...

متن کامل

Use of Artificial Neural Networks and PCA to Predict Results of Infertility Treatment in the ICSI Method

Background: Intracytoplasmic sperm injection (ICSI) or microinjection is one of the most commonly used assisted reproductive technologies (ART) in the treatment of patients with infertility problems. At each stage of this treatment cycle, many dependent and independent variables may affect the results, according to which, estimating the accuracy of fertility rate for physicians will be difficul...

متن کامل

Neural Network Performance Analysis for Real Time Hand Gesture Tracking Based on Hu Moment and Hybrid Features

This paper presents a comparison study between the multilayer perceptron (MLP) and radial basis function (RBF) neural networks with supervised learning and back propagation algorithm to track hand gestures. Both networks have two output classes which are hand and face. Skin is detected by a regional based algorithm in the image, and then networks are applied on video sequences frame by frame in...

متن کامل

A Fast Approach to the Detection of All-Purpose Hubs in Complex Networks with Chemical Applications

A novel algorithm for the fast detection of hubs in chemical networks is presented. The algorithm identifies a set of nodes in the network as most significant, aimed to be the most effective points of distribution for fast, widespread coverage throughout the system. We show that our hubs have in general greater closeness centrality and betweenness centrality than vertices with maximal degree, w...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1995