- ホーム
- > 洋書
- > ドイツ書
- > Mathematics, Sciences & Technology
- > Technology
- > electronics, electrical engineering, telecommunications
Full Description
This is the first textbook focusing on practicality of machine learning (ML) and deep neural networks (DNN), by introducing methods that enable engineering applications of ML and DNN models. The authors describe many methodologies that are widely used in designing, training, and deploying of these models and discuss their applicability under various contexts. Coverage begins with the basic knowledge of machine learning and deep neural networks and their applications in solving practical engineering problems. It then proceeds through a series of computer engineering methods commonly used in developing machine learning and deep neural network models. The book also explains how to improve the training and inference performance in terms of model accuracy, size, runtime, etc. by considering various requirements and availability of data in the applications. Techniques that are widely adopted in both industry and academia are discussed. Tutorials and projects designed to practice the introduced techniques are provided using popular development frameworks of machine learning.
Emphasizes practice over theoretical foundations, making content accessible to engineering students and engineers;
Includes in-depth discussion of popular DNN models and their applications;
Discusses engineering methods and tricks widely adopted in practice for using ML and DNN to solve engineering problems.
Contents
Introduction.- Perceptron and back propagation.- Image feature and 2d convolution.- Convolutional neural network.- Efficient neural architecture.- Recurrent neural network and language models.- Transfer learning.- Generative adversarial network gan.- Automl and neural architecture search.- Distributed computing and federated learning.- Summary.
