This book offers a timely snapshot and extensive practical and theoretical insights into the topic of learning from data. Based on the tutorials presented at the INNS Big Data and Deep Learning Conference, INNSBDDL2019, held on April 16-18, 2019, in Sestri Levante, Italy, the respective chapters cover advanced neural networks, deep architectures, and supervised and reinforcement machine learning models. They describe important theoretical concepts, presenting in detail all the necessary mathematical formalizations, and offer essential guidance on their use in current big data research.

This book is intended for a first course on microprocessor-based systems design for engineering and computer science students. It starts with an introduction of the fundamental concepts, followed by a practical path that guides readers to developing a basic microprocessor example, using a step-by-step problem-solving approach. Then, a second microprocessor is presented, and readers are guided to the implementation and programming of microcomputer systems based on it. The numerous worked examples and solved exercises allow a better understanding and a more effective learning. All the examples and exercises were developed on Deeds (Digital Electronics Education and Design Suite), which is freely available online on a website developed and maintained by the authors. The discussed examples can be simulated by using Deeds and the solutions to all exercises and examples can be found on that website. Further, in the last part of this book, different microprocessor-based systems, which have been specifically thought for educational purposes, are extensively developed, simulated and implemented on FPGA-based platforms. This textbook draws on the authors' extensive experience in teaching and developing learning materials for bachelor's and master's engineering courses. It can be used for self-study as well, and even independently from the simulator. Thanks to the learning-by-doing approach and the plentiful examples, no prior knowledge in computer programming is required.

This book has been designed for a first course on digital design for engineering and computer science students. It offers an extensive introduction on fundamental theories, from Boolean algebra and binary arithmetic to sequential networks and finite state machines, together with the essential tools to design and simulate systems composed of a controller and a datapath. The numerous worked examples and solved exercises allow a better understanding and more effective learning. All of the examples and exercises can be run on the Deeds software, freely available online on a webpage developed and maintained by the authors. Thanks to the learning-by-doing approach and the plentiful examples, no prior knowledge in electronics of programming is required. Moreover, the book can be adapted to different level of education, with different targets and depth, be used for self-study, and even independently from the simulator. The book draws on the authors' extensive experience in teaching and developing learning materials.

This book presents the original articles that have been accepted in the 2019 INNS Big Data and Deep Learning (INNS BDDL) international conference, a major event for researchers in the field of artificial neural networks, big data and related topics, organized by the International Neural Network Society and hosted by the University of Genoa. In 2019 INNS BDDL has been held in Sestri Levante (Italy) from April 16 to April 18. More than 80 researchers from 20 countries participated in the INNS BDDL in April 2019. In addition to regular sessions, INNS BDDL welcomed around 40 oral communications, 6 tutorials have been presented together with 4 invited plenary speakers. This book covers a broad range of topics in big data and deep learning, from theoretical aspects to state-of-the-art applications. This book is directed to both Ph.D. students and Researchers in the field in order to provide a general picture of the state-of-the-art on the topics addressed by the conference.

This book is intended for a first course on microprocessor-based systems design for engineering and computer science students. It starts with an introduction of the fundamental concepts, followed by a practical path that guides readers to developing a basic microprocessor example, using a step-by-step problem-solving approach. Then, a second microprocessor is presented, and readers are guided to the implementation and programming of microcomputer systems based on it. The numerous worked examples and solved exercises allow a better understanding and a more effective learning. All the examples and exercises were developed on Deeds (Digital Electronics Education and Design Suite), which is freely available online on a website developed and maintained by the authors. The discussed examples can be simulated by using Deeds and the solutions to all exercises and examples can be found on that website. Further, in the last part of this book, different microprocessor-based systems, which have been specifically thought for educational purposes, are extensively developed, simulated and implemented on FPGA-based platforms. This textbook draws on the authors' extensive experience in teaching and developing learning materials for bachelor's and master's engineering courses. It can be used for self-study as well, and even independently from the simulator. Thanks to the learning-by-doing approach and the plentiful examples, no prior knowledge in computer programming is required.

This book offers a timely snapshot and extensive practical and theoretical insights into the topic of learning from data. Based on the tutorials presented at the INNS Big Data and Deep Learning Conference, INNSBDDL2019, held on April 16-18, 2019, in Sestri Levante, Italy, the respective chapters cover advanced neural networks, deep architectures, and supervised and reinforcement machine learning models. They describe important theoretical concepts, presenting in detail all the necessary mathematical formalizations, and offer essential guidance on their use in current big data research.

How can we select the best performing data-driven model? How can we rigorously estimate its generalization error? Statistical learning theory answers these questions by deriving non-asymptotic bounds on the generalization error of a model or, in other words, by upper bounding the true error of the learned model based just on quantities computed on the available data. However, for a long time, Statistical learning theory has been considered only an abstract theoretical framework, useful for inspiring new learning approaches, but with limited applicability to practical problems. The purpose of this book is to give an intelligible overview of the problems of model selection and error estimation, by focusing on the ideas behind the different statistical learning theory approaches and simplifying most of the technical aspects with the purpose of making them more accessible and usable in practice. The book starts by presenting the seminal works of the 80's and includes the most recent results. It discusses open problems and outlines future directions for research.

This book has been designed for a first course on digital design for engineering and computer science students. It offers an extensive introduction on fundamental theories, from Boolean algebra and binary arithmetic to sequential networks and finite state machines, together with the essential tools to design and simulate systems composed of a controller and a datapath. The numerous worked examples and solved exercises allow a better understanding and more effective learning. All of the examples and exercises can be run on the Deeds software, freely available online on a webpage developed and maintained by the authors. Thanks to the learning-by-doing approach and the plentiful examples, no prior knowledge in electronics of programming is required. Moreover, the book can be adapted to different level of education, with different targets and depth, be used for self-study, and even independently from the simulator. The book draws on the authors' extensive experience in teaching and developing learning materials.