Advanced Deep Learning with TensorFlow 2 and Keras

Rowel Atienza is an Associate Professor at the University of the Philippines, Diliman's Electrical and Electronics Engineering Institute. He is the Dado and Maria Banatao Institute Professorial Chair in Artificial Intelligence, and his work on an AI-enhanced four-legged robot earned him an MEng from the National University of Singapore.

The bestselling book on advanced deep learning techniques available today, Advanced Deep Learning with TensorFlow 2 and Keras, Second Edition, has been substantially updated. With additional chapters on unsupervised learning utilizing mutual information, object detection (SSD), and semantic segmentation (FCN and PSPNet) for TensorFlow 2. x, this version introduces you to the practical side of deep learning, letting you develop your own cutting-edge AI projects.

The book begins with an overview of multi-layer perceptrons (MLPs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs), before moving on to deeper neural network architectures, such as ResNet and DenseNet, and how to develop autoencoders. Then you'll learn about GANs and how they can help AI to new heights.

Following that, you'll learn how to use a variational autoencoder (VAE) and how GANs and VAEs have the generative power to create data that is incredibly convincing to humans. You'll also learn how to use DRL, such as Deep Q-Learning and Policy Gradient Methods, to achieve many of today's AI outcomes.

What you will learn:

• To achieve unsupervised learning, use mutual information maximization strategies.
• Segmentation is a technique for determining the pixel-by-pixel class of each object in a picture.
• Using object detection, determine the bounding box and class of objects in a picture.
• MLPs, CNNs, and RNNs are the building blocks for advanced approaches.
• Recognize deep neural networks, such as ResNet and DenseNet.
• Autoencoders, VAEs, and GANs are examples of autoregressive models to learn about and construct.
• Methods for deep reinforcement learning must be discovered and implemented.

Some reviews about this book: "Great visuals, code, and math. The book delivers what the deep learning practitioner needs: advanced content with replicable and reproducible results. I highly recommend this great book by Rowel Atienza."; "Advanced Deep Learning with TensorFlow 2 and Keras - Second Edition is a good and big step into an advanced practice direction. It's a brilliant book and I consider this as a must-read for all."

Author: Rowel Atienza

Check price: https://www.amazon.com/Advanced-Deep-Learning-TensorFlow-Keras/dp/1838821651?