Deep Learning Workshop:

Theory, Algorithms, and Applications


May 24-28, 2015
University Residential Center
Bertinoro (Forlì-Cesena), Italy

The workshop aims to bring together leading scientists in deep learning and related areas within machine learning, artificial intelligence, mathematics, statistics, and neuroscience. The workshop is supported by the Bertinoro International Center for Informatics and has an informal structure. No formal submission is required and participation is by invitation only. Participants are invited to present their recently published work as well as work in progress, and share their vision and perspectives for the field. The 2014 edition of the meeting was held in Shonan, Japan.

News: Next year's Deep Learning Workshop will be held at MIT (Center for Brains, Minds, and Machines) in Boston on June 10-12, 2016

Overview

The ability to learn is essential to the survival and robustness of biological systems. There is also growing evidence that learning is essential to build robust artificial intelligent systems and solve complex problems in most application domains. Indeed, one of the success stories in computer science over the past three decades has been the emergence of machine learning and data mining algorithms as tools for solving large-scale problems in a variety of domains such as computer vision, speech recognition, natural language understanding, robotics, and bioinformatics. However, we are still far from having a complete understanding of machine learning and its role in AI, and plenty of challenges, both theoretical and practical, remain to be addressed.

Complex problems cannot be solved in one single step and often require multiple processing stages in both natural and artificial systems. For instance, visual recognition in humans is not instantaneous and requires activation of a hierarchy of processing stages and pathways. The same is true for all the best performing computer vision systems available today. Thus deep learning architectures, comprising multiple, adaptable, processing layers are important for the understanding and design of both natural and artificial systems and, today, are at the forefront of machine learning research. In the past year alone, deep learning methods have achieved state-of-the-art performance in many application areas. It is this recent wave of progress that provides the relevant background for the workshop which will focus on all aspects of deep architectures and deep learning, with a particular emphasis on understanding fundamental principles. A major thrust of the meeting will be to foster theoretical analyses of deep learning. In addition to theory, topics to be covered include algorithms and applications, including novel applications beyond the traditional engineering domains, such as applications to the natural sciences . The primary intellectual focus of the meeting will be on deep learning in artificial systems. However, deep learning draws some of its inspiration from, and has close connections to, neuroscience. Thus presentations and discussions bridging learning in natural and artificial learning systems will also be encouraged.