May 29, 2019 (09:00 - 10:00 PST)
Training deep neural networks can take a long time on a single machine. Learn how three deep learning frameworks optimized for Intel® architecture can speed up the process.
Jun 5, 2019 (09:00 - 10:00 PST)
Reducing model precision is an efficient way to accelerate inference while still achieving high performance on low-precision processors.
Jun 19, 2019 (09:00 - 10:00 PST)
Find out how Threading Building Blocks Memory Allocator can meet your memory management needs.