Delving into the deeply enigmatic nature of Artificial Intelligence (AI), AI: Unexplainable, Unpredictable, Uncontrollable explores the various reasons why the field is so challenging. Written by one of the founders of the field of AI safety, this book addresses some of the most fascinating questions facing humanity, including the nature of intelligence, consciousness, values and knowledge. Moving from a broad introduction to the core problems, such as the unpredictability of AI outcomes or the difficulty in explaining AI decisions, this book arrives at more complex questions of ownership and control, conducting an in-depth analysis of potential hazards and unintentional consequences. The book then concludes with philosophical and existential considerations, probing into questions of AI personhood, consciousness, and the distinction between human intelligence and artificial general intelligence (AGI). Bridging the gap between technical intricacies and philosophical musings, AI: Unexplainable, Unpredictable, Uncontrollable appeals to both AI experts and enthusiasts looking for a comprehensive understanding of the field, whilst also being written for a general audience with minimal technical jargon.

Over the past decade, a number of hardware and software advances have conspired to thrust deep learning and neural networks to the forefront of computing. Deep learning has created a qualitative shift in our conception of what software is and what it can do: Every day we're seeing new applications of deep learning, from healthcare to art, and it feels like we're only scratching the surface of a universe of new possibilities. This book offers the first introduction of foundational ideas from automated verification as applied to deep neural networks and deep learning. It is divided into three parts: Part 1 defines neural networks as data-flow graphs of operators over real-valued inputs. Part 2 discusses constraint-based techniques for verification. Part 3 discusses abstraction-based techniques for verification. The book is a self-contained treatment of a topic that sits at the intersection of machine learning and formal verification. It can serve as an introduction to the field for first-year graduate students or senior undergraduates, even if they have not been exposed to deep learning or verification.

This book constitutes the refereed proceedings of the 9th International Symposium on Automated Technology for Verification and Analysis, ATVA 2011, held in Taipei, Taiwan, in October 2011. The 23 revised regular papers presented together with 5 invited papers, 11 short papers, and 2 tool papers, were carefully reviewed and selected from 75 submissions. The papers address all theoretical and practical aspects of automated analysis, verification and synthesis; thus providing a forum for interaction between the regional and the international research communities and industry in the field.

The open access two-volume set LNCS 12224 and 12225 constitutes the refereed proceedings of the 32st International Conference on Computer Aided Verification, CAV 2020, held in Los Angeles, CA, USA, in July 2020.* The 43 full papers presented together with 18 tool papers and 4 case studies, were carefully reviewed and selected from 240 submissions. The papers were organized in the following topical sections: Part I: AI verification; blockchain and Security; Concurrency; hardware verification and decision procedures; and hybrid and dynamic systems. Part II: model checking; software verification; stochastic systems; and synthesis. *The conference was held virtually due to the COVID-19 pandemic.

This volume gives the proceedings of the Fourth Workshop on Computer-Aided Verification (CAV '92), held in Montreal, June 29 - July 1, 1992. The objective of this series of workshops is to bring together researchers and practitioners interested in the development and use of methods, tools and theories for the computer-aided verification of concurrent systems. The workshops provide an opportunity for comparing various verification methods and practical tools that can be used to assist the applications designer. Emphasis is placed on new research results and the application of existing results to real verification problems. The volume contains 31 papers selected from 75 submissions. These are organized into parts on reduction techniques, proof checking, symbolic verification, timing verification, partial-order approaches, case studies, model and proof checking, and other approaches. The volume starts with an invited lecture by Leslie Lamport entitled "Computer-hindered verification (humans can do it too)".

This book constitutes the refereed proceedings of the 19th International Conference on Runtime Verification, RV 2019, held in Porto, Portugal, in October 2019. The 25 regular papers presented in this book were carefully reviewed and selected from 38 submissions. The RV conference is concerned with all aspects of monitoring and analysis of hardware, software and more general system executions. Runtime verification techniques are lightweight techniques to assess system correctness, reliability, and robustness; these techniques are significantly more powerful and versatile than conventional testing, and more practical than exhaustive formal verification. Chapter “Assumption-Based Runtime Verification with Partial Observability and Resets” and chapter “NuRV: a nuXmv Extension for Runtime Verification“ are available open access under a Creative Commons Attribution 4.0 International License via link.springer.com.

This book constitutes the refereed proceedings of the 20th International Symposium on Automated Technology for Verification and Analysis, ATVA 2022, held in Beiging, China in October 2022. The symposium is dedicated to promoting research in theoretical and practical aspects of automated analysis, verification and synthesis by providing an international venue for the researchers to present new results. The 21 regular papers presented together with 5 tool papers and 1 invited paper were carefully reviewed and selected from 81 submissions. The papers are divided into the following topical sub-headings: reinforcement learning; program analysis and verification; smt and verification; automata and applications; active learning; probabilistic and stochastic systems; synthesis and repair; and verification of neural networks.

During the last few years, we have seen quite spectacular progress in the area of approximation algorithms: for several fundamental optimization problems we now actually know matching upper and lower bounds for their approximability. This textbook-like tutorial is a coherent and essentially self-contained presentation of the enormous recent progress facilitated by the interplay between the theory of probabilistically checkable proofs and aproximation algorithms. The basic concepts, methods, and results are presented in a unified way to provide a smooth introduction for newcomers. These lectures are particularly useful for advanced courses or reading groups on the topic.