One Epoch means the total dataset is passed forward and backward in a neural network once.
Since one epoch will be large to feed to the neural network at once, we have to divide it into multiple batches.
Suppose, we have 2000 training examples we are going to train on.
We can split the dataset into batches of 500 and then it will take 4 iterations for one epoch.
If you want to learn Machine Learning and implement ML applications, you can enroll in this Machine Learning Course by Intellipaat.