Learn to design and build deep learning models with Keras
Key Features
- Learn how to use more advanced techniques required to develop state-of-the-art deep learning models
- Learn how to use advanced image augmentation techniques in order to lift model performance
- Learn how to enhance performance with learning rate schedules
Book Description
Welcome to hands-on Keras for machine learning engineers. This is a carefully structured course to guide you in your journey to learn deep learning in Python with Keras. Discover the Keras Python library for deep learning and learn the process of developing and evaluating deep learning models using it.
There are two top numerical platforms for developing deep learning models; they are Theano, developed by the University of Montreal, and TensorFlow developed at Google. Both were developed for use in Python and both can be leveraged by the super-simple-to-use Keras library. Keras wraps the numerical computing complexity of Theano and TensorFlow, providing a concise API that we will use to develop our own neural network and deep learning models. Keras has become the gold standard in the applied space for rapid prototyping deep learning models.
This course is a hands-on guide. It is a playbook and a workbook intended for you to learn by doing and then apply your new understanding to your own deep learning Keras models.
All resources and code files for this course are placed here: https://github.com/PacktPublishing/Hands-On-Keras-for-Machine-Learning-Engineers
What you will learn
- Develop and evaluate neural network models end-to-end
- Build larger models for image and text data
- Understand the anatomy of a Keras model
- Evaluate the performance of a deep learning Keras model
- Build end-to-end regression and classification models in Keras
- Learn how to use checkpointing to save the best model run
Who this book is for
This course is for developers, machine learning engineers, and data scientists that want to learn how to get the most out of Keras. You do not need to be a machine learning expert, but it would be helpful if you knew how to navigate a small machine learning problem using SciKit-Learn. Basic concepts such as cross-validation and one-hot encoding used in lessons and projects are described, but only briefly. With all of this in mind, this is an entry-level course on the Keras library.
