# Hello Deep Learning: Dropout, data augmentation, weight decay and quantisation

DevFeed: [Hello Deep Learning: Dropout, data augmentation, weight decay and quantisation](<https://devfeed.tech/articles/hello-deep-learning-dropout-data-augmentation-weight-decay-and-quantisation-36368.md>)

Original publisher: [Read original article](<https://berthub.eu/articles/posts/dropout-data-augmentation-weight-decay/>)

Published: 2023-03-30T10:00:07Z

Content type: tutorial

Language: en

Sources: [Bert Hubert's writings](<https://devfeed.tech/sources/bert-hubert-s-writings.md>)

Topics: [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [image](<https://devfeed.tech/tags/image.md>), [performance](<https://devfeed.tech/tags/performance.md>), [training](<https://devfeed.tech/tags/training.md>), [training-data](<https://devfeed.tech/tags/training-data.md>), [validation](<https://devfeed.tech/tags/validation.md>)

## AI overview

This Hello Deep Learning tutorial examines how data augmentation and related techniques can improve the robustness of a convolutional handwritten-digit recognition network. It explains that exposing the network to shifted, corrupted, or otherwise modified inputs helps it handle real-world variation and can enlarge a limited training set.

## Source excerpt

This page is part of the Hello Deep Learning series of blog posts. You are very welcome to improve this page via GitHub! In the previous chapter we found ways to speed up our character recognition learning by a factor of 20 by using a better optimizer, and a further factor of four by cleverly using threads using a 'shared nothing architecture'. We also learned how we can observe the development of parameters.