Artificial Intelligent Systems and Machine Learning

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

An Overview of Artificial Neural Networks: Part 1


Affiliations
1 Department of Electronics and Telecommunication Engineering, Sinhgad College of Engineering, Pune
2 Sinhgad College of Science, Pune, and Maharashtra, India
3 Department of Electronics and Telecommunication Engineering, Sinhgad College of Engineering, Pune, India
4 Department of Electronics and Telecommunication Engineering, Sinhgad College of Engineering, Pune, India
     

   Subscribe/Renew Journal


This paper presents the basic concepts of Artificial Neural Networks (ANNs) which helps to beginners of ANN. The need of soft computing, terms and the different trends related with Soft Computing (SC) is discussed in the introductory part. The architecture of ANN has been described with the help of structure of Biological Neural Network. The different thresholding techniques used for converting actual mathematical values into decision is also given. The concept of weight adjustment has been elaborated with the help of line fitting problem. The terms gradient and steepest descent have been explained with help of examples. Gradient descent algorithm is explained which helps to beginner of ANN with the help of MATLAB Code.  The results are discussed for line fitting. The parameters like Minimum Cost Function (CF), Iteration and Learning Rate are discussed. The final values of weights are in terms of slope and intercept are presented for line fitting.


Keywords

Artificial Neural Network, Gradient Descent, Line Fitting, Soft Computing, Steepest Descent.
User
Subscription Login to verify subscription
Notifications
Font Size


  • An Overview of Artificial Neural Networks: Part 1

Abstract Views: 334  |  PDF Views: 1

Authors

R. B. Dhumale
Department of Electronics and Telecommunication Engineering, Sinhgad College of Engineering, Pune
M. P. Ghatule
Sinhgad College of Science, Pune, and Maharashtra, India
N. D. Thombare
Department of Electronics and Telecommunication Engineering, Sinhgad College of Engineering, Pune, India
P. M. Bangare
Department of Electronics and Telecommunication Engineering, Sinhgad College of Engineering, Pune, India

Abstract


This paper presents the basic concepts of Artificial Neural Networks (ANNs) which helps to beginners of ANN. The need of soft computing, terms and the different trends related with Soft Computing (SC) is discussed in the introductory part. The architecture of ANN has been described with the help of structure of Biological Neural Network. The different thresholding techniques used for converting actual mathematical values into decision is also given. The concept of weight adjustment has been elaborated with the help of line fitting problem. The terms gradient and steepest descent have been explained with help of examples. Gradient descent algorithm is explained which helps to beginner of ANN with the help of MATLAB Code.  The results are discussed for line fitting. The parameters like Minimum Cost Function (CF), Iteration and Learning Rate are discussed. The final values of weights are in terms of slope and intercept are presented for line fitting.


Keywords


Artificial Neural Network, Gradient Descent, Line Fitting, Soft Computing, Steepest Descent.

References