6.825 Hardware Architecture for Deep Learning (New)


Class Info

Introduction to the design and implementation of hardware architectures for efficient processing of deep learning algorithms in AI systems. Topics include basics of deep learning, programmable platforms, accelerators, co-optimization of algorithms and hardware, training, support for complex networks, and applications of advanced technologies. Includes labs involving modeling and analysis of hardware architectures, building systems using popular deep learning tools and platforms (CPU, GPU, FPGA), and an open-ended design project. Students taking graduate version complete additional assignments.

This class has 6.003, and 6.004 as prerequisites.

6.825 will not be offered this semester. It will be available in the Spring semester, and will be instructed by .

This class counts for a total of 12 credits. This is a graduate-level class.

You can find more information on MIT OpenCourseWare at the Techniques in Artificial Intelligence (SMA 5504) site or on the 6.825 Stellar site.

MIT 6.825 Hardware Architecture for Deep Learning (New) Related Textbooks
MIT 6.825 Hardware Architecture for Deep Learning (New) On The Web
Techniques in Artificial Intelligence (SMA 5504)
Tags
first order logic representation artificial intelligence

© Copyright 2015