Abstract: A major advance in AI occurred in 2012 when AlexNet won the ImageNet competition with a deep network.  The success was sufficiently better than previous years that deep networks were applied in many applications with great success.  However, there is little understanding of why deep learning works.  This talk will give an introduction to machine learning and then illustrate current research directions in deep learning at a level for a general scientific audience.

 

Biography：John Hopcroft received the Turing Award, the most prestigious award in the field and often recognized as the "Nobel Prize of computing" (jointly with Robert Tarjan) "for fundamental achievements in the design and analysis of algorithms and data structures." Along with his work with Tarjan on planar graphs he is also known for the Hopcroft–Karp algorithm for finding matchings in bipartite graphs. In 1994 he was inducted as a Fellow of the Association for Computing Machinery. In 2005 he received the Harry H. Goode Memorial Award "for fundamental contributions to the study of algorithms and their applications in information processing." In 2008 he received the Karl V. Karlstrom Outstanding Educator Award "for his vision of and impact on computer science, including co-authoring field-defining texts on theory and algorithms, which continue to influence students 40 years later, advising PhD students who themselves are now contributing greatly to computer science, and providing influential leadership in computer science research and education at the national and international level."