Marco Gori

The remarkable progress in computer vision over the last few years is, by and large, attributed to deep learning, fueled by the availability of huge sets of labeled data, and paired with the explosive growth of the GPU paradigm. While subscribing to this view, this work criticizes the supposed scientific progress in the field, and proposes the investigation of vision within the framework of information-based laws of nature. This work poses fundamental questions about vision that remain far from understood, leading the reader on a journey populated by novel challenges resonating with the foundations of machine learning. The central thesis proposed is that for a deeper understanding of visual computational processes, it is necessary to look beyond the applications of general purpose machine learning algorithms, and focus instead on appropriate learning theories that take into account the spatiotemporal nature of the visual signal.Serving to inspire and stimulate critical reflection and discussion, yet requiring no prior advanced technical knowledge, the text can naturally be paired with classic textbooks on computer vision to better frame the current state of the art, open problems, and novel potential solutions. As such, it will be of great benefit to graduate and advanced undergraduate students in computer science, computational neuroscience, physics, and other related disciplines.

Machine Learning: A Constraint-Based Approach provides readers with a refreshing look at the basic models and algorithms of machine learning, with an emphasis on current topics of interest that includes neural networks and kernel machines. The book presents the information in a truly unified manner that is based on the notion of learning from environmental constraints. While regarding symbolic knowledge bases as a collection of constraints, the book draws a path towards a deep integration with machine learning that relies on the idea of adopting multivalued logic formalisms, like in fuzzy systems. A special attention is reserved to deep learning, which nicely fits the constrained- based approach followed in this book. This book presents a simpler unified notion of regularization, which is strictly connected with the parsimony principle, and includes many solved exercises that are classified according to the Donald Knuth ranking of difficulty, which essentially consists of a mix of warm-up exercises that lead to deeper research problems. A software simulator is also included.

Web Dragons offers a perspective on the world of Web search and the effects of search engines and information availability on the present and future world. In the blink of an eye since the turn of the millennium, the lives of people who work with information have been utterly transformed. Everything we need to know is on the web. It's where we learn and play, shop and do business, keep up with old friends and meet new ones. Search engines make it possible for us to find the stuff we need to know. Search engines — web dragons — are the portals through which we access society's treasure trove of information. How do they stack up against librarians, the gatekeepers over centuries past? What role will libraries play in a world whose information is ruled by the web? How is the web organized? Who controls its contents, and how do they do it? How do search engines work? How can web visibility be exploited by those who want to sell us their wares? What's coming tomorrow, and can we influence it? As we witness the dawn of a new era, this book shows readers what it will look like and how it will change their world. Whoever you are: if you care about information, this book will open your eyes and make you blink.