Danilo Pau
Unified the AI tool stands: Introducing the ST Core AI Technology
Danilo Pau
Technical Director, IEEE AAIA & ST Fellow, APSIPA Life Member
ABSTRACT
Tiny Machine Learning engineers urge new tools to help them to be more productive than ever to develop innovative AI solutions at the edge. When devising applications for humanoid robotics, mobility, consumer, IoT, medical, industrial etc. any fragmentation in the workflow with respect to the underlying products to be adopted severely limit their creativity and capability to achieve fast deployment into the market.
The AI Unified Core Technology has been created as a common code generator across products to address this challenge and to act as the enabling unifying AI technology to serve many, even heterogeneous, product generations.
This technology interfaces the most widely used Deep Learning representations such as Keras, QKeras and Tensorflow Lite and the Open Neural Network Exchange (ONNX). It outputs optimized C code. Moreover, it makes available public APIs to deploy applications on STM32, Stellar MCUs and AI MEMs sensors thus easing developers workflow and to finalize their application of choice with unprecedented speed.
SPEAKER BIOGRAPHY
Danilo Pau (h-index 28, i10-index 73) graduate in 1992 at Politecnico di Milano, Italy. On 1991, he joined SGS-THOMSON (now STMicroelectronics) as interns on Advanced Multimedia Architectures, and he worked on memory reduced HDMAC HW design. Some exemplary project he worked on were: MPEG2 video memory reduction; video coding, transcoding, embedded (Khronos) 2/3D graphics, and (ISO CDVS and CDVA) computer vision. Currently, his work focuses on the ST unified AI core technology integrated into company tools (STM32Cube.AI, Stellar.AI, SPC-Studio.AI, MEMs Studio).
Danilo is an IEEE Fellow, 2019; AAIA Fellow on 2023; ST fellow on 2022 and APSIPA Life Member.
In IEEE he is a Member of the Machine Learning, Deep Learning and AI in the CE (MDA) Technical Stream Committee CESoc. He wrote the IEEE Milestone on Multiple Silicon Technologies on a chip, 1985 which was ratified by IEEE BoD in 2021 and IEEE Milestone on MPEG Multimedia Integrated Circuits, 1984-1993 which was ratified in 2022. He serves as TPC member to TinyML Symposium and Summit as well as Talks series and much more, and as 2022/3 IEEE Computer Society Fellow Evaluating Committee Members. With 81 and 68 respectively European and US application patents, 181 publications, 113 ISO/IEC/MPEG authored documents and 90 invited talks/seminars at various Universities and Conferences, Danilo's favorite activity remains supervising undergraduate students, MSc engineers and PhDs
