Bounds on the number of hidden neurons in three-layer binary neural networks

نویسندگان

  • Zhaozhi Zhang
  • Xiaomin Ma
  • Yixian Yang
چکیده

This paper investigates an important problem concerning the complexity of three-layer binary neural networks (BNNs) with one hidden layer. The neuron in the studied BNNs employs a hard limiter activation function with only integer weights and an integer threshold. The studies are focused on implementations of arbitrary Boolean functions which map from [0, 1]n into [0, 1]. A deterministic algorithm called set covering algorithm (SCA) is proposed for the construction of a three-layer BNN to implement an arbitrary Boolean function. The SCA is based on a unit sphere covering (USC) of the Hamming space (HS) which is chosen in advance. It is proved that for the implementation of an arbitrary Boolean function of n-variables (n > or = 3) by using SCA, [3L/2] hidden neurons are necessary and sufficient, where L is the number of unit spheres contained in the chosen USC of the n-dimensional HS. It is shown that by using SCA, the number of hidden neurons required is much less than that by using a two-parallel hyperplane method. In order to indicate the potential ability of three-layer BNNs, a lower bound on the required number of hidden neurons which is derived by using the method of estimating the Vapnik-Chervonenkis (VC) dimension is also given.

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

Prediction of breeding values for the milk production trait in Iranian Holstein cows applying artificial neural networks

The artificial neural networks, the learning algorithms and mathematical models mimicking the information processing ability of human brain can be used non-linear and complex data. The aim of this study was to predict the breeding values for milk production trait in Iranian Holstein cows applying artificial neural networks. Data on 35167 Iranian Holstein cows recorded between 1998 to 2009 were ...

متن کامل

Artificial Neural Networks (ANN) for the simultaneous spectrophotometric determination of fluoxetine and sertraline in pharmaceutical formulations and biological fluid

Simultaneous spectrophotometric estimation of Fluoxetine and Sertraline in tablets were performed using UV–Vis spectroscopic and Artificial Neural Networks (ANN). Absorption spectra of two components were recorded in 200–300 (nm) wavelengths region with an interval of 1 nm. The calibration models were thoroughly evaluated at several concentration levels using the spectra of synthetic binary mix...

متن کامل

Artificial Neural Networks (ANN) for the simultaneous spectrophotometric determination of fluoxetine and sertraline in pharmaceutical formulations and biological fluid

Simultaneous spectrophotometric estimation of Fluoxetine and Sertraline in tablets were performed using UV–Vis spectroscopic and Artificial Neural Networks (ANN). Absorption spectra of two components were recorded in 200–300 (nm) wavelengths region with an interval of 1 nm. The calibration models were thoroughly evaluated at several concentration levels using the spectra of synthetic binary mix...

متن کامل

Evaluation of effects of operating parameters on combustible material recovery in coking coal flotation process using artificial neural networks

In this research work, the effects of flotation parameters on coking coal flotation combustible material recovery (CMR) were studied by the artificial neural networks (ANNs) method. The input parameters of the network were the pulp solid weight content, pH, collector dosage, frother dosage, conditioning time, flotation retention time, feed ash content, and rotor rotation speed. In order to sele...

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:
  • Neural networks : the official journal of the International Neural Network Society

دوره 16 7  شماره 

صفحات  -

تاریخ انتشار 2003