Video Series: Hands-On AI | Part 1: Introduction


In this video series, learn how image data preprocessing can be used to clean and augment transformations on a dataset and why it matters.


Hey, I'm Karl, the AI developer community manager for Intel. This is Hands-On AI, a five-part series that will cover image data preprocessing and augmentation in order to use it as a clean data set for machine learning applications. This series will also give you an idea of how to prepare your data set so that it is ready to be digested by a machine learning training program, with a specific end application in mind.

For example, if you were building an app that showed an image that related to the mood of the music playing, you'd want to make sure you're showing the right image to match that mood. Let's talk about what's included in this series.

First, we discover data cleaning and the best ways to do it. Next, we cover different ways to augment your data. Finally, we show how to combine all these in our specific use case. For this, we have picked a data set with positive and negative examples. There are a lot of them out there, so the specific data set isn't incredibly important. We then show you how to do image data preprocessing and augmentation. Preprocessing is a series of steps that prepares our data set for ingestion into a machine learning algorithm. Augmentation is then taking that clean data and modifying it to prepare our model for real-world scenarios.

The images we focus on for this series are divided into two categories: positive and negative. The machine learning algorithm will then associate these images with a particular mood. The techniques introduced in this series can be used on any data set, images or otherwise.

Hands-On AI is useful for you if your data set is small, you want to get an accurate model, or you want to ensure that your model is prepared for a real-world application. Things we will not be covering in this series are how to train a model or how to build an application using that model. However, if you are interested in these steps, please read the full article associated with this series on the Intel® Developer Zone.

Thanks for watching Hands-On AI. Catch our next episode about data cleaning and be sure to check out the links to learn more about AI through the Intel® AI Developer Program.

Product and Performance Information


Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice revision #20110804