Jerry An
1 min readApr 3, 2020

--

Batch size vs epochs

Batch Size:

How many training data size is used each time when the model parameter is updated?

For example, the batch size of Stochastic Gradient Descent is one. While the batch size of Gradient Descent equals to the whole training data size. Mini Batch Gradient Descent is in between them.

Epochs :

When the ENRITE training data is used only ONCE, it’s called one epoch. Epochs stand for how many times the whole training data is used repeatedly?

Sign up to discover human stories that deepen your understanding of the world.

Free

Distraction-free reading. No ads.

Organize your knowledge with lists and highlights.

Tell your story. Find your audience.

Membership

Read member-only stories

Support writers you read most

Earn money for your writing

Listen to audio narrations

Read offline with the Medium app

--

--

Jerry An
Jerry An

No responses yet

Write a response