Hopfield Neural Networks for Timetabling: Formulations, Methods, and Comparative Results

نویسندگان

  • Kate A. Smith
  • David Abramson
  • David Duke
چکیده

This paper considers the use of discrete Hopfield neural networks for solving school timetabling problems. Two alternative formulations are provided for the problem: a standard Hopfield-Tank approach, and a more compact formulation which allows the Hopfield network to be competitive with swapping heuristics. It is demonstrated how these formulations can lead to different results. The Hopfield network dynamics are also modified to allow it to be competitive with other metaheuristics by incorporating controlled stochasticities. These modifications do not complicate the algorithm, making it possible to implement our Hopfield network in hardware. The neural network results are evaluated on benchmark data sets and are compared to results obtained using greedy search, simulated annealing and tabu search.

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 Evolutionary Approach to the School Timetabling Problem

We present a general heuristic technique that solves a timetabling problem, such as school timetabling. It is based on a Hopfield-type neural network, whose complexity was significantly reduced by incorporating a genetic algorithm into a very first stage of the timetabling process. The goal of the GA was to initialize the network so that the number of neurons and their connections decreased, an...

متن کامل

The Comparative Analysis of Two Neural Networks Models in the Function of the Linear Ship’s Route Costs Minimization the Comparative Analysis of Two Neural Networks Models in the Function of the Linear Ship’s Route Costs Minimization

The paper deals with a comparison between two different methods in generating sub-optimal solutions to the Hopfield-Tank TSP (traveling salesman problem) neural algorithm. Namely, the Hopfield-Tank TSP neural algorithm has been applied in the paper to the linear ship’s route, that is cycle voyage modeling, which means here finding the optimal visiting order of a given set of ports in such way a...

متن کامل

Enhanced Formulations for Call Capacity Improvement of Distributed DCA Schemes Based on Hopfield Neural Networks

DCA schemes based on Hopfield Neural Networks have been shown to perform favourably compared to more traditional schemes [5][9]. Furthermore, the use of distributed schemes as opposed to centralised schemes has shown to be effective in channel allocation dealing with smaller cells which is typical of emerging 3G systems [13]. The work reported in this paper extends that of [9] by considering a ...

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

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 2002