Bøger af Paulo Shakarian

This book provides a broad overview of the key results and frameworks for various NSAI tasks as well as discussing important application areas. This book also covers neuro symbolic reasoning frameworks such as LNN, LTN, and NeurASP and learning frameworks. This would include differential inductive logic programming, constraint learning and deep symbolic policy learning. Additionally, application areas such a visual question answering and natural language processing are discussed as well as topics such as verification of neural networks and symbol grounding. Detailed algorithmic descriptions, example logic programs, and an online supplement that includes instructional videos and slides provide thorough but concise coverage of this important area of AI. Neuro symbolic artificial intelligence (NSAI) encompasses the combination of deep neural networks with symbolic logic for reasoning and learning tasks. NSAI frameworks are now capable of embedding priorknowledge in deep learning architectures, guiding the learning process with logical constraints, providing symbolic explainability, and using gradient-based approaches to learn logical statements. Several approaches are seeing usage in various application areas. This book is designed for researchers and advanced-level students trying to understand the current landscape of NSAI research as well as those looking to apply NSAI research in areas such as natural language processing and visual question answering. Practitioners who specialize in employing machine learning and AI systems for operational use will find this book useful as well.

This SpringerBrief discusses how to develop intelligent systems for cyber attribution regarding cyber-attacks. Specifically, the authors review the multiple facets of the cyber attribution problem that make it difficult for "out-of-the-box" artificial intelligence and machine learning techniques to handle.  Attributing a cyber-operation through the use of multiple pieces of technical evidence (i.e., malware reverse-engineering and source tracking) and conventional intelligence sources (i.e., human or signals intelligence) is a difficult problem not only due to the effort required to obtain evidence, but the ease with which an adversary can plant false evidence. This SpringerBrief not only lays out the theoretical foundations for how to handle the unique aspects of cyber attribution - and how to update models used for this purpose - but it also describes a series of empirical results, as well as compares results of specially-designed frameworks for cyber attribution to standard machine learning approaches.  Cyber attribution is not only a challenging problem, but there are also problems in performing such research, particularly in obtaining relevant data. This SpringerBrief describes how to use capture-the-flag for such research, and describes issues from organizing such data to running your own capture-the-flag specifically designed for cyber attribution. Datasets and software are also available on the companion website.

It introduces diffusion models from the fields of computer science (independent cascade and linear threshold), sociology (tipping models), physics (voter models), biology (evolutionary models), and epidemiology (SIR/SIS and related models).

Imagine yourself as a military officer in a conflict zone trying to identify locations of weapons caches supporting road-side bomb attacks on your country's troops. Geospatial Abduction provides the mathematics underlying geospatial abduction and the algorithms to solve them in practice;