We held our next tinyML Talks webcast. Ashutosh Pandey from Infineon Technologies presented Exploring techniques to build efficient and robust TinyML deployments on January 18, 2022.
Data is key to designing effective deep learning applications, where characteristics and availability of data vary from application to application. Edge deployment of deep learning methods requires privacy, low power usage, and robustness against out-of-distribution data. Furthermore, data for training and deployment tasks, often referred to as the training dataset and the calibration dataset, respectively, may not be available in some applications. In this talk, trade-offs between power and performance, given the availability of training data for supervised learning, will be highlighted. In addition, a dynamic fixed-point quantization scheme suitable for edge deployment in absence of sufficient calibration data will be presented, and trade-offs in compute resource for quantization, such as memory and cycles, will be discussed. Finally, edge deployment architecture utilizing deep learning methods to handle out-of-distribution data due to sensor degradation and alien operating conditions will be presented.
Ashutosh Pandey is currently a Lead Principal Systems Engineer at Infineon Technologies where he is responsible for Machine learning solutions, architecture, and tooling. He holds a PhD from the University of Utah and has over 40 papers and patents on speech/audio/machine learning systems and algorithms.
Watch on YouTube:
Download presentation slides:
Feel free to ask your questions on this thread and keep the conversation going!