Efficient Processing for Deep Learning: Challenges and Opportunities скачать в хорошем качестве

Efficient Processing for Deep Learning: Challenges and Opportunities

Dr. Vivienne Sze, Associate Professor in the Electrical Engineering and Computer Science Department at MIT (www.rle.mit.edu/eems) presents a one-hour webinar, "Efficient Processing for Deep Learning: Challenges and Opportunities," organized by the Embedded Vision Alliance. Deep neural networks (DNNs) are proving very effective for a variety of challenging machine perception tasks. But these algorithms are very computationally demanding. To enable DNNs to be used in practical applications, it’s critical to find efficient ways to implement them. This webinar explores how DNNs are being mapped onto today’s processor architectures, and how both DNN algorithms and specialized processors are evolving to enable improved efficiency. Sze concludes with suggestions on how to evaluate competing processor solutions in order to address your particular application and design requirements.