Murali Akula, Senior Director of Software Engineering at Qualcomm, joins us today. Murali’s role at Qualcomm, where he leads the corporate research team focused on the development and deployment of AI onto Snapdragon chips, their unique definition of “full-stack,” and how that philosophy permeates every step of the software development process, are all discussed in our interview.
We look at the complexities that come with doing machine learning on resource-constrained devices, some of the techniques used to get complex models working on mobile devices, and the process for moving these models from research to real-world applications. We also go over some other tools and recent developments, such as DONNA for neural architecture search, X-Distill, a method for improving self-supervised monocular depth training, and the AI Model Efficiency Toolkit, a library that provides advanced quantization and compression techniques for trained neural network models.
Source link
