A Comprehensive Evaluation of Weight Growth and Weight Elimination Methods Using the Tangent Plane Algorithm

نویسندگان

  • P May
  • C. W. Lee
چکیده

The tangent plane algorithm is a fast sequential learning method for multilayered feedforward neural networks that accepts almost zero initial conditions for the connection weights with the expectation that only the minimum number of weights will be activated. However, the inclusion of a tendency to move away from the origin in weight space can lead to large weights that are harmful to generalization. This paper evaluates two techniques used to limit the size of the weights, weight growing and weight elimination, in the tangent plane algorithm. Comparative tests were carried out using the Extreme Learning Machine which is a fast global minimiser giving good generalization. Experimental results show that the generalization performance of the tangent plane algorithm with weight elimination is at least as good as the ELM algorithm making it a suitable alternative for problems that involve time varying data such as EEG and ECG signals. Keywords—neural networks; backpropagation; generalization; tangent plane; weight elimination; extreme learning machine

برای دانلود رایگان 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

Improved Generalization in Recurrent Neural Networks Using the Tangent Plane Algorithm

The tangent plane algorithm for real time recurrent learning (TPA-RTRL) is an effective online training method for fully recurrent neural networks. TPA-RTRL uses the method of approaching tangent planes to accelerate the learning processes. Compared to the original gradient descent real time recurrent learning algorithm (GD-RTRL) it is very fast and avoids problems like local minima of the sear...

متن کامل

Enhanced Comprehensive Learning Cooperative Particle Swarm Optimization with Fuzzy Inertia Weight (ECLCFPSO-IW)

So far various methods for optimization presented and one of most popular of them are optimization algorithms based on swarm intelligence and also one of most successful of them is Particle Swarm Optimization (PSO). Prior some efforts by applying fuzzy logic for improving defects of PSO such as trapping in local optimums and early convergence has been done. Moreover to overcome the problem of i...

متن کامل

Prediction of Structural Changes in Gas Hydrate for Methane and Ethane Mixture by Using Tangent Plane Distance Minimization

Abstract:  In this study, the change in the crystalline structure of gas hydrate was predicted for ternary mixture of methane-ethane-water. For this purpose, the tangent plane distance (TPD) minimization method was used. First, the calculations were performed for the binary mixtures of methane-water and ethane-water as the gas and liquid phases. The results show that for a binary mixture of th...

متن کامل

تعیین نورموگرام رشد دانش آموزان دختر 11-14 ساله شهر بیرجند در سال 1383 و مقایسه آن با مقادیر مرجع مرکز آمارهای بهداشتی

Background and Aim: Measurement of weight and height is very important source of information in evaluation of growth, nutrition and health of children and adolescence. Since, the growth is affected by genetic, racial, geographical and environmental factors, the growth charts differ from one population to another. The aim of this study was Measurement of weight and height of girls’ students in ...

متن کامل

Nonlinear inelastic static analysis of plane frames with numerically generated tangent stiffness matrices

For the nonlinear analysis of structures using the well known Newton-Raphson Method, the tangent stiffness matrices of the elements must be constructed in each iteration. Due to the high expense required to find the exact tangent stiffness matrices, researchers have developed novel innovations into the Newton-Raphson method to reduce the cost and time required by the analysis. In this paper, a ...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013