In the rapidly evolving field of Tiny Machine Learning (TinyML), custom microcontrollers offer unmatched performance and power efficiency for AI applications. However, the traditional route of designing and implementing custom ASICs (Application-Specific Integrated Circuits) often comes with prohibitively high Non-Recurring Engineering (NRE) costs, making it a daunting endeavor for many.
In this talk, we will unveil an innovative ecosystem that transcends the barriers posed by NRE costs. Our comprehensive solution comprises open-source tools, a robust methodology, a thriving community, and access to fabrication services. This ecosystem empowers you to design and implement custom microcontrollers optimized for TinyML applications without the financial burden of traditional ASIC development.
Schedule
Timezone: PDT
Unlocking TinyML: A Cost-Efficient Approach to Custom Microcontroller Design for AI Applications
Mohamed SHALAN, Head of Design and EDA
Efabless Corporation
Mohamed SHALAN, Head of Design and EDA
Efabless Corporation
Mohamed Shalan is the Head of Design and EDA at Efabless Corporation. Before his role with Efabless, Mohamed held various engineering positions at several organizations, including Mentor Graphics, Motorola SPS, and Mindspeed. Mohamed holds a Ph.D. degree in computer engineering from the Georgia Institute of Technology. His research interests are multifaceted, encompassing open-source EDA, hardware, and software codesign for embedded systems, with a strong emphasis on low-power computing. His contributions to these areas have resulted in over 40 peer-reviewed publications and three US patents.
Schedule subject to change without notice.