Come along to a Distinguished Lecture hosted by Platform Technologies Research Institute, entitled, Learning architectures and training algorithms - comparative studies. It will be presented by Professor Bogdan M. Wilamowski, Director of Alabama Nano/Micro Science and Technology Center and Alumna Professor, Electrical and Computer Engineering at Auburn University, Alabama. Date: Monday 12 January 2015 Time: 2:00pm – 3:00pm (afternoon tea provided) Location: RMIT City Campus Council Chamber, Building 1, Level 2, Room 17 RSVP: [email protected] Abstract The traditional approach for solving complex problems and processes was to try to understand them, then try to describe them in the form of mathematical formulas. This classical Da Vinci approach however, cannot be applied to many current complex problems, which are very difficult to understand and process by humans. Many environmental, economic, and often engineering problems cannot be described by equations, and it seems that adaptive learning architectures are the only solution to tackling these complex problems. It has already been demonstrated that much higher capabilities of super compact architectures have 10 to 100 times more processing power than commonly used learning architectures like MLP. It turns out that the power of learning systems grows linearly with their widths and exponentially with their depth. Therefore, a natural approach would be to use these deep architectures. Unfortunately, because of the vanishing gradient problem, these deep architectures are very difficult to train, so a mixture of approaches is used with a partial success. Until now, it has been considered impossible to train neural networks with more than 6 hidden layers. We have demonstrated that it is possible to efficiently train much deeper networks through the introduction of additional connections across layers and to use our new very powerful NBN algorithm. Information about the presenter is available on the attached flyer. Please feel free to distribute this information to any of your colleagues who may be interested in attending. Platform Technologies Research Institute RMIT University Tel: (03) 9925 8362 Email: [email protected] rmit.edu.au/research/institutes/platformtechnologies
Posted on: Thu, 08 Jan 2015 01:36:37 +0000
Trending Topics
Recently Viewed Topics
© 2015