Yong Cheng – författare

How is it possible to allow multiple data owners to collaboratively train and use a shared prediction model while keeping all the local training data private?

Traditional machine learning approaches need to combine all data at one location, typically a data center, which may very well violate the laws on user privacy and data confidentiality. Today, many parts of the world demand that technology companies treat user data carefully according to user-privacy laws. The European Union''s General Data Protection Regulation (GDPR) is a prime example. In this book, we describe how federated machine learning addresses this problem with novel solutions combining distributed machine learning, cryptography and security, and incentive mechanism design based on economic principles and game theory. We explain different types of privacy-preserving machine learning solutions and their technological backgrounds, and highlight some representative practical use cases. We show how federated learning can become the foundation of next-generation machine learning that caters to technological and societal needs for responsible AI development and application.

This book presents four approaches to jointly training bidirectional neural machine translation (NMT) models. First, in order to improve the accuracy of the attention mechanism, it proposes an agreement-based joint training approach to help the two complementary models agree on word alignment matrices for the same training data. Second, it presents a semi-supervised approach that uses an autoencoder to reconstruct monolingual corpora, so as to incorporate these corpora into neural machine translation. It then introduces a joint training algorithm for pivot-based neural machine translation, which can be used to mitigate the data scarcity problem. Lastly it describes an end-to-end bidirectional NMT model to connect the source-to-target and target-to-source translation models, allowing the interaction of parameters between these two directional models.

This book investigates the creation of healthy and thermally comfortable built environments in a low-carbon manner with advanced air distribution, i.e., stratum ventilation. Stratum ventilation efficiently supplies conditioned and clean air to the head level of occupants for thermal comfort and inhaled air quality and largely reduces energy consumption and CO2 emission, e.g., by 44% and 32%, respectively, compared with the conventional air distribution method. This book provides the working principles, performance evaluations methods, design methods, operation methods, and different application scenarios (particularly highlighting airborne infection risk control of respiratory diseases and integrated application with renewable energy) of stratum ventilation, to provide theoretical understandings and technical guidelines of stratum ventilation. The book is intended for undergraduate and graduate students, researchers, and engineers who are interested in cutting-edge technologies of livable and sustainable built environments.