Articles → MACHINE LEARNING → Loss Function In Machine Learning

Loss Function In Machine Learning

This article describes the Loss Function in Machine Learning.

Purpose

In machine learning, a loss function (also referred to as a cost function or objective function) is a mathematical function that measures the accuracy of a model's performance.

It tells us how far the model’s predictions are from the actual (true) values. The goal of training is to minimize the loss function, i.e., make predictions as close as possible to the real outputs.

Types Of Loss Functions

For Regression Problems - Mean Squared Error (MSE) and Mean Absolute Error (MAE).
For Classification Problems - Cross-Entropy Loss and Hinge Loss.

Example

Imagine you predict house prices.

The actual price = ₹50 lakh.
Model predicts = ₹45 lakh
Error = ₹5 lakh

The loss function converts this error into a numeric penalty.

Posted By -	Karan Gupta

Posted On -	Thursday, September 25, 2025

Query/Feedback

Your Email Id		**

Subject		*

Query/Feedback	Characters remaining 250	**