A Multi-Sieving Neural Network Architecture That Decomposes Learning Tasks Automatically

نویسنده

  • BAO-LIANG Lu
چکیده

This paper presents a multi-sieving network (MSN) architecture and a multi-sieving learning (MSL) algorithm for it. The basic idea behind MSN architecture is the multi-sieve method, that is, patterns are classified by a rough sieve at the beginning and done by finer ones gradually. MSN is constructed by adding a sieving module (SM) adaptively with progress of training. SM consists of two different neural networks and a simple logical circuit. MSL algorithm starts with a single SM, then does the following three phases repeatedly until all the training samples are successfully learned: (a) the learning phase in which the training samples are learned by the current SM, (b) the sieving phase in which the training samples that have been successfully learned are sifted out from the training set, and (c) the growing phase in which the current SM is frozen and a new S M is added in order to learn the remaining training samples. MSN architecture has several attractive properties such as automatic decomposition of learning tasks, modular structure, easy implementation of additional learning, overcoming a problem of local minima and fast convergence. The performance of MSN architecture is illustrated on two benchmark problems.

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

A Parallel and Modular Multi - Sieving Neural Network Architecture for Constructive Learning

In this paper we present a parallel and modular multi-sieving neural network (PMSN) architecture for constructive learning. This PMSN architecture is dierent from existing constructive learning networks such as the cascade correlation architecture. The constructing element of the PMSNs is a compound modular network rather than a hidden unit. This compound modular network is called a sieving mod...

متن کامل

Learning Document Image Features With SqueezeNet Convolutional Neural Network

The classification of various document images is considered an important step towards building a modern digital library or office automation system. Convolutional Neural Network (CNN) classifiers trained with backpropagation are considered to be the current state of the art model for this task. However, there are two major drawbacks for these classifiers: the huge computational power demand for...

متن کامل

Multi-Step-Ahead Prediction of Stock Price Using a New Architecture of Neural Networks

Modelling and forecasting Stock market is a challenging task for economists and engineers since it has a dynamic structure and nonlinear characteristic. This nonlinearity affects the efficiency of the price characteristics. Using an Artificial Neural Network (ANN) is a proper way to model this nonlinearity and it has been used successfully in one-step-ahead and multi-step-ahead prediction of di...

متن کامل

Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi-Task Learning

Deep learning (DL) advances state-of-the-art reinforcement learning (RL), by incorporating deep neural networks in learning representations from the input to RL. However, the conventional deep neural network architecture is limited in learning representations for multi-task RL (MT-RL), as multiple tasks can refer to different kinds of representations. In this paper, we thus propose a novel deep...

متن کامل

An Unsupervised Learning Method for an Attacker Agent in Robot Soccer Competitions Based on the Kohonen Neural Network

RoboCup competition as a great test-bed, has turned to a worldwide popular domains in recent years. The main object of such competitions is to deal with complex behavior of systems whichconsist of multiple autonomous agents. The rich experience of human soccer player can be used as a valuable reference for a robot soccer player. However, because of the differences between real and simulated soc...

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 2004