Amita Kapoor Reihenfolge der Bücher (Chronologisch)

Learn to build advanced machine and deep learning systems for various environments with this comprehensive guide. It covers neural networks and deep learning techniques using TensorFlow and Keras, focusing on writing applications within the powerful and scalable machine learning framework. The latest version, TensorFlow 2.x, emphasizes simplicity and user-friendliness, featuring updates like eager execution, intuitive APIs based on Keras, and flexible model building across platforms. The content provides an overview of supervised and unsupervised machine learning models, along with an in-depth analysis of deep learning and reinforcement learning through practical examples applicable to cloud, mobile, and large-scale production settings. The book details the creation of neural networks with TensorFlow and explores popular algorithms, including regression, convolutional neural networks (CNNs), transformers, generative adversarial networks (GANs), recurrent neural networks (RNNs), natural language processing (NLP), and graph neural networks (GNNs). Additionally, it includes working example applications and discusses TensorFlow in production, mobile, and AutoML contexts. Aimed at Python developers and data scientists, this hands-on resource equips readers with both the theoretical knowledge and practical skills necessary to develop machine learning systems using Keras, TensorFlow, and AutoML, with some prior machine learning k

Build machine and deep learning systems with TensorFlow 2 and Keras for lab, production, and mobile devices. This resource introduces TensorFlow 2 and Keras from the outset, teaching essential machine and deep learning techniques through clear explanations and extensive code samples. The second edition focuses on neural networks and deep learning alongside TensorFlow and Keras, enabling the creation of deep learning applications using a powerful and scalable machine learning stack. TensorFlow is the preferred library for professional applications, while Keras provides a user-friendly Python API for TensorFlow access. The book covers various applications, including regression, convolutional networks (CNNs), generative adversarial networks (GANs), recurrent neural networks (RNNs), and natural language processing (NLP). It includes two practical example apps and discusses deploying TensorFlow in production and mobile environments, as well as utilizing AutoML. Readers will learn to build machine learning systems, apply regression analysis, understand CNNs for image classification, generate new data with GANs, process sequences with RNNs, and automate ML workflows using Google tools. This book is ideal for Python developers and data scientists looking to enhance their machine learning and deep learning expertise with TensorFlow and Keras, assuming some prior knowledge of the field.