International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064


Downloads: 120 | Views: 381 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1

Research Paper | Computer Science & Engineering | India | Volume 3 Issue 8, August 2014 | Popularity: 6.7 / 10


     

Adaptation to Best Fit Learning Rate in Batch Gradient Descent

Mohan Pandey, B. L. Pal


Abstract: The efficient training of a supervised machine learning system is commonly viewed as minimization of a cost function that depends on the parameters of the proposed hypothesis. This perspective gives some advantages to the development of better training algorithm, as the problem of minimization of a function is well known in many fields. Typically many learning system use gradient descent to minimize the cost function but has a problem of slow convergence and exploding on choosing learning rate beyond a threshold. We often make mistake on choosing learning rate as there is no known generic way of choosing learning rate and we need to do it manually. In this paper a method for the adaptation of learning rate is presented and also solving the problem of slow convergence and exploding of the algorithm. The main feature of proposed algorithm is that it speeds up the convergence rate and does not affect the result or number of epochs requires to converge on changing the learning rate.


Keywords: Batch training, On-line training, Epoch, Learning Rate, Gradient Descent, Hypothesis, Cost Function


Edition: Volume 3 Issue 8, August 2014


Pages: 16 - 20



Make Sure to Disable the Pop-Up Blocker of Web Browser


Text copied to Clipboard!
Mohan Pandey, B. L. Pal, "Adaptation to Best Fit Learning Rate in Batch Gradient Descent", International Journal of Science and Research (IJSR), Volume 3 Issue 8, August 2014, pp. 16-20, https://www.ijsr.net/getabstract.php?paperid=2015173

Similar Articles

Downloads: 3 | Weekly Hits: ⮙2 | Monthly Hits: ⮙2

Research Paper, Computer Science & Engineering, India, Volume 11 Issue 5, May 2022

Pages: 1480 - 1485

Feature Selection for Handwriting Digit Recognition Using Convolutional Neural Network

Tarun Patel, Shivansh Tiwari, Vaibhav Dubey, Vaibhav Singh, Dr. Harvendra Kumar

Share this Article

Downloads: 109

Research Paper, Computer Science & Engineering, India, Volume 4 Issue 6, June 2015

Pages: 1592 - 1597

Privacy Conserving Gradient Descent Method Applied for Neural Network with Distributed Datasets

Sachin P. Yadav, Amit B. Chougule

Share this Article

Downloads: 110

Survey Paper, Computer Science & Engineering, India, Volume 4 Issue 11, November 2015

Pages: 1325 - 1328

A Survey of Different Prediction Models & Role of Artificial Neural Networks for Natural Gas Consumption

Prabodh K Pradhan, Sunil Dhal

Share this Article

Downloads: 112

Survey Paper, Computer Science & Engineering, India, Volume 3 Issue 11, November 2014

Pages: 1494 - 1496

Survey of Novel Process for Domain Adaptation and Cost Sensitive Online Classification in Data Mining

Ashish. S. Kale, S. P. Kosbatwar

Share this Article

Downloads: 115

Survey Paper, Computer Science & Engineering, India, Volume 3 Issue 11, November 2014

Pages: 2677 - 2680

Survey of Novel Method for Online Classification in Data Mining

Jadhav Bharat S, Gumaste S.V.

Share this Article
Top