We held our next tinyML Talks webcast. Ilya Gozman from Grovety presented Minimizing resource usage in microcontrollers for cost effective solutions on September 26, 2023.
The spotlight will be on Fine-Tuning strategy - approach that plays a critical role in optimizing neural network inference. We’ll illustrate how Apache TVM, an open-source machine learning compiler, significantly aids in reducing device cost and energy consumption.
We’ll also discuss our choice of Micro TVM and Arm Ethos-U55 on Alif E5 SoC, detailing their unique advantages and how they align with our goals, and revealing the results of our optimization efforts.
Finally, we’ll provide an exciting sneak peek into the future of our TinyML efforts, including upcoming products, our goal to further refine networks while maintaining accuracy, and our innovative strategies for ongoing optimization and development in the TinyML field.
Ilya is a Senior Fellow and a Chief AI Architect at Grovety, where he worked out his way from a rising talent developer to a veteran expert in AI, a frontline and prospective trend in IT-industry in recent years. He acquired extensive experience in developing general and AI compilers, and chip architectures both in LLVM and TVM backend optimizations; he also led teams working on compiling-related projects, video processing, and protocols support for IP cameras (C/C++). Ilya received Master degree in Applied Mathematics and Computer Science in 2007. Wide range of projects and profound research activity makes Ilya’s experience valuable and demanded.
=========================
Watch on YouTube:
Ilya Gozman
Download presentation slides:
Ilya Gozman
Feel free to ask your questions on this thread and keep the conversation going!