In this liveProject, you’ll learn and apply some of the basics of deep learning in order to build the foundations of an AutoML image classifier. You’ll discover the basic deep learning models for image classification, and then experiment with tuning the hyperparameters of a convolutional neural network to improve your results.

In this liveProject, you’ll learn how to use the Task and Functional API of Keras to build an automated deep learning model for image classification. This AutoML approach will allow you to avoid time spent selecting and tuning your deep learning algorithms. You’ll work with the detailed CIFAR dataset of animal images which is easy to access through the TensorFlow Keras API.

In this liveProject, you’ll utilize automated machine learning tools to help the data preprocessing and feature engineering for creating an image classification model. You’ll start with the basics of data preprocessing, and then see how useful AutoML solutions can make this process quicker and easier. The rewards are big, as properly preprocessed data can dramatically improve the outcomes of a deep learning project.

In this liveProject, you’ll implement an AutoML pipeline using the AutoKeras functional API. You’ll make use of the built-in blocks in AutoKeras to conduct automated hyperparameter tuning and model selection for creating an image classification model. Your challenges will include customizing both a sequential AutoML pipeline, and customizing graph-structured AutoML Pipeline.

In this liveProject, you’ll build an AutoKeras block for image classification to help tune a neural network and customize the search space. You’ll then combine the block you have created with other prebuilt AutoKeras blocks to put together a complete automated machine learning pipeline.