ARC Processor Summit Proceedings
Taming AI Using Convolutional Neural Networks with Compression and Pruning
To implement AI applications at the edge, you need to move from training to inference on your embedded target. This transition comes with a new set of considerations to take into account. For the target system, you must consider factors such as performance, memory size, throughput, and bandwidth, as well as maintaining the accuracy of your graph. In this session, we will show how you can profile your graph and then achieve your design targets with techniques such as feature-map compression, graph acceleration and coefficient pruning.
Bo Wu, Applications Engineer, Synopsys
Thank you for your interest in the presentations from the event.
Please complete the registration form and click the 'continue >>' button below.