New Serial Titles


Book Description













Electronic Materials Handbook


Book Description

Volume 1: Packaging is an authoritative reference source of practical information for the design or process engineer who must make informed day-to-day decisions about the materials and processes of microelectronic packaging. Its 117 articles offer the collective knowledge, wisdom, and judgement of 407 microelectronics packaging experts-authors, co-authors, and reviewers-representing 192 companies, universities, laboratories, and other organizations. This is the inaugural volume of ASMAs all-new ElectronicMaterials Handbook series, designed to be the Metals Handbook of electronics technology. In over 65 years of publishing the Metals Handbook, ASM has developed a unique editorial method of compiling large technical reference books. ASMAs access to leading materials technology experts enables to organize these books on an industry consensus basis. Behind every article. Is an author who is a top expert in its specific subject area. This multi-author approach ensures the best, most timely information throughout. Individually selected panels of 5 and 6 peers review each article for technical accuracy, generic point of view, and completeness.Volumes in the Electronic Materials Handbook series are multidisciplinary, to reflect industry practice applied in integrating multiple technology disciplines necessary to any program in advanced electronics. Volume 1: Packaging focusing on the middle level of the electronics technology size spectrum, offers the greatest practical value to the largest and broadest group of users. Future volumes in the series will address topics on larger (integrated electronic assemblies) and smaller (semiconductor materials and devices) size levels.




Reinforcement Learning, second edition


Book Description

The significantly expanded and updated new edition of a widely used text on reinforcement learning, one of the most active research areas in artificial intelligence. Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the field's key ideas and algorithms. This second edition has been significantly expanded and updated, presenting new topics and updating coverage of other topics. Like the first edition, this second edition focuses on core online learning algorithms, with the more mathematical material set off in shaded boxes. Part I covers as much of reinforcement learning as possible without going beyond the tabular case for which exact solutions can be found. Many algorithms presented in this part are new to the second edition, including UCB, Expected Sarsa, and Double Learning. Part II extends these ideas to function approximation, with new sections on such topics as artificial neural networks and the Fourier basis, and offers expanded treatment of off-policy learning and policy-gradient methods. Part III has new chapters on reinforcement learning's relationships to psychology and neuroscience, as well as an updated case-studies chapter including AlphaGo and AlphaGo Zero, Atari game playing, and IBM Watson's wagering strategy. The final chapter discusses the future societal impacts of reinforcement learning.