Our Director of ML Architecture Lawrence Spracklen will be the closing keynote speaker and our VP of Research and Engineering Subutai Ahmad will be a session panelist for the Edge AI Summit on September 14th.
Achieving full optimization requires co-design and co-optimization of AI algorithms and the hardware platforms where they will be executed. Subutai, along with CEO and founder of ThirdAI, Anshumali Shrivastava will explore the benefits and potential of such co-design approaches.
In this presentation, Lawrence will discuss how leveraging sparsity, knowledge distillation and quantization, not only enable deep learning models to run on edge devices, but in many instances outperform standard models running on datacenter class systems. We discuss our recent innovations in sparsity research that enables the creation of dual-sparse networks that can outperform standard networks by over 100X. Finally, we illustrate how sparsity can be combined with other model compression techniques to unlock deep learning inference at the edge.
Edge AI Summit:
The 5th Annual Edge AI Summit unites the technologists from around the world tasked with designing and developing real-world use cases that bring real-time and secure AI to low-power applications from the sensor-edge to device-edge, and to areas that have limited connectivity to the cloud. Register here.