In Machine learning, gradient descent is an optimization algorithm used to find the parameters that minimize the cost function. Cost function represents the goodness of the model in predictions for those weights. In gradient descent, we start off randomly initializing values and slowly moves towards the steepest descent until the convergence point. We can adjust the size of steps by hyperparameter called the learning rate.
You can check out this Machine learning certification by Intellipaat to learn Machine learning.
You can watch this video on Machine learning Full course to learn more about gradient descent: