One of the core ideas of machine learning is that it learns via optimization. Gradient descent is an optimization algorithm that learns iteratively. Here gradient refers to the small change, and descent refers to rolling down. The idea is, the error or loss will roll down with small steps, eventually reaching the minimum loss. The …
Guide to Gradient Descent: Working Principle and its Variants Read More »
Welcome to the second part of the Complete Guide to Loss Functions. Previously we had studied the Regression Losses in depth. In this blog, we will go through the details of the Classification Loss Functions. Classification algorithms like Logistic Regression, SVM (Support Vector Machines), Neural Networks use a specific set of loss functions for the …
A Beginner’s Guide to Loss functions for Classification Algorithms Read More »
A Beginner’s Guide to Loss functions for Regression Algorithms An in-depth explanation for widely used regression loss functions like mean squared error, mean absolute error, and Huber loss. Loss function in supervised machine learning is like a compass that gives algorithms a sense of direction while learning parameters or weights. This blog will explain the …
A Beginner’s Guide to Loss functions for Regression Algorithms Read More »
