Event details Event cancelled
Platform Technologies Research Institute Distinguished Lecture: Learning architectures and training algorithms - comparative studies.
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.
- Professor Bogdan M. Wilamowski, Director of Alabama Nano/Micro Science and Technology Center
- Alumna Professor, Electrical and Computer Engineering at Auburn University, Alabama
Registration and bookings
Afternoon tea provided.