tiny ML Talks Toronto Part 1: Evolutionary Needs of Tiny ML
tinyML Talks Toronto Part 1 Evolutionary Needs of TinyML Liang Shen, Sr. Director of Engineering Qualcomm During the past decade, Deep Learning based AI technology not only becomes the predominant solutions for existing or new problems, also almost instantly deployed to various smart devices. In this talk, we start with a brief review on how powerefficient AI engine helped this new AI wave and effectively enabled billions of batterypowered devices; then, we touch the new trend: alwayson or longcontinuousrun AI use cases, which require optimal minimum power solution. We discuss some details of ultralowpower AI solution and how it offers the improved quality for targeted use cases. With continuous evolution of new intelligent algorithms, this talk concludes with ongoing challenges and some potential directions.
|
|