Gradient Descent Variants

-

Gradient descent variants

There are three variants of gradient descent, which differ in how much data we use to compute the gradient of the objective function. Depending on the amount of data, we make a trade-off between the accuracy of the parameter update and the time it takes to perform an update.

  • Gradient descent variants
    • Batch gradient descent
    • Stochastic gradient descent
    • Mini-batch gradient descent




Comments

  1. Taletreedesign24 February 2022 at 18:20


    Hi dear,

    Thank you for this wonderful post. It is very informative and useful. I would like to share something here too.Se sei disoccupato e ricevi sussidi, puoi imparare GRATUITAMENTE. I corsi si svolgono durante il giorno e la sera. La priorità sui corsi diurni è data ai disoccupati. Un corso giornaliero è gratuito per tutti i disoccupati; Ottieni i corsi gratuiti per disoccupati online.


    Corsi di formazione

    ReplyDelete
  2. Helpful Insight Pvt. Ltd.27 February 2022 at 09:02

    Hi dear,

    Thank you for this wonderful post. It is very informative and useful. I would like to share something here too.Our highly professional team provide complete IT solutions that specializes in custom mobile and web application development. Call us at (+91) 9001721837.


    cms development company

    ReplyDelete
  3. venkateshj8 May 2022 at 22:38

    That is good post and have useful information to learn. I really liked your work you had done. Please go through our website Selenium Training in Bangalore and this course will also help others to learn which has good future.

    ReplyDelete
  4. Digital Arnav13 April 2024 at 03:13

    One of the standout features of APTRON Solutions is its hands-on approach to learning. Students are not just taught the theory behind the Machine Learning Training Institute in Noida algorithms but are also given ample opportunities to apply their knowledge in real-world scenarios. Through projects and case studies, learners gain invaluable experience that prepares them for challenges they may encounter in their future careers.

    ReplyDelete

Post a Comment

Popular posts from this blog

Linear Regression with single variable

-
Image
Linear Regression Algorithm From Andrew Ng’s Machine learning course The above diagram conveniently gives a brief overview of the Linear Regression Algorithm. We feed our learning algorithm with some data set(training set), which then outputs a function called Hypothesis. Hypothesis approximates a target function for mapping inputs to outputs. For linear regression in one variable, our hypothesis function is of the form — h(x) = θ0 + θ1x where θ0 and θ1 are the parameters.
Read more

Introduction Deep Learning

-
Deep learning is a branch of  machine learning   which is completely based on   artificial neural networks , as the neural network is going to mimic the human brain so deep learning is also a kind of mimic of the human brain. In deep learning, we don’t need to explicitly program everything. The concept of deep learning is not new. It has been around for a couple of years now. It’s on hype nowadays because earlier we did not have that much processing power and a lot of data. As in the last 20 years, the processing power increases exponentially, deep learning and machine learning came in the picture. A formal definition of deep learning is- neurons "Deep learning is a particular kind of machine learning that achieves great  power and flexibility by learning to represent the world as a nested hierarchy of concepts, with each concept defined in relation to simpler concepts, and more abstract representations computed in terms of less abstract ones". In the human brain approximatel
Read more

Decision Tree

-
Decision Tree Classification Algorithm A decision Tree is a  Supervised learning technique  that can be used for both classification and Regression problems, but mostly it is preferred for solving Classification problems. It is a tree-structured classifier, where  internal nodes represent the features of a dataset, branches represent the decision rules  and  each leaf node represents the outcome. In a Decision tree, there are two nodes, which are the  Decision Node  and  Leaf Node.  Decision nodes are used to make any decision and have multiple branches, whereas Leaf nodes are the output of those decisions and do not contain any further branches. The decisions or the test are performed on the basis of features of the given dataset. It is a graphical representation for getting all the possible solutions to a problem/decision based on given conditions. It is called a decision tree because similar to a tree, it starts with the root node, which expands on further branches and constructs a
Read more