Slidecast: Deep Learning – Unreasonably Effective

In this slidecast, Stephen Jones from Nvidia presents: Deep Learning – Unreasonably Effective.

Deep Learning is a new area of Machine Learning research, which has been introduced with the objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence. At the 2015 GPU Technology Conference, you can join the experts who are making groundbreaking improvements in a variety of deep learning applications, including image classification, video analytics, speech recognition, and natural language processing.

With deep learning, a neural network learns many levels of abstraction. They range from simple concepts to complex ones. This is what puts the “deep” in deep learning. Each layer categorizes some kind of information, refines it and passes it along to the next. Deep learning lets a machine use this process to build a hierarchical representation. So, the first layer might look for simple edges (computer vision researchers call these “Gabor filters”). The next might look for collections of edges that form simple shapes like rectangles, or circles. The third might identify features like eyes and noses. After five or six layers, the neural network can put these features together. The result: a machine that can recognize faces. GPUs are ideal for this, speeding a process that could otherwise take a year or more to just weeks or days. That’s because GPUs perform many calculations at once—or in parallel. And once a system is “trained,” with GPUs, scientists and researchers can put that learning to work.

Download the MP3Subscribe on iTunes * Subscribe to RSS 

Sign up for our insideHPC Newsletter.