Lecture Series Archive

Abstract – The Global Technology Supply Chain is an AND world! As electronic instruments and products become more complex, and more prevalent, designers are challenged to design state of the art equipment that is state of the art AND cost competitive AND environmentally responsible. In this lecture we will explore what a global technology supply chain is and how design choices engineers make during the initial product design can be optimized for a cost effective and “greener” global supply chain. We will look at the concept of “Design for Supply Chain.” Design is a series of trade-offs and the design of a supply chain is no different. Various countries around the world have comparative advantage for certain aspects of the supply chain and designers need to be cognizant of these strengths and also the cost, risk, and environmental impact tradeoffs associated with these choices. Finally, we will explore engineering jobs that are needed within the enterprise supply chain function.

Mr. Patrick Harper is the Vice President and General Manager of the Technology Order Fulfillment team at Keysight Technologies. He manages a team of over 1000 employees worldwide and has team members in Germany, Geneva, Spain, UK, Finland, Penang Malaysia and the US. Pat has been in the high tech industry for over 35 years including 20 years with Hewlett Packard and 13 with Agilent Technologies, and two years with Keysight Technologies. He has held a variety of positions in Manufacturing and R&D. He has a BS in Economics and a MS in Project Management from the University of San Francisco and is PMP certified. In his “spare time” he is an adjunct professor at the University of San Francisco and Sonoma State University teaching a variety of undergrad and graduate courses. Pat currently serves on the board of two non-profits and is very involved in STEM programs and projects across Sonoma County.

Abstract – Convolutional Neural Networks (CNNs) have led to remarkable breakthroughs in a number of important pattern recognition tasks, such as image and voice recognition. Modern CNNs are composed of many layers, have millions (sometimes billions) of parameters, and require massive amount of computation to train them. The training is typically performed using large amount of data on massively-parallel servers equipped with graphics processing units (GPUs). Subsequently, the trained models are utilized in many application scenarios to run 'inference' on user's data, often on resourceconstrained mobile devices. The computational demand of running modern CNNs creates interesting technical challenges, in particular as it relates to deployment of trained models to resourceconstrained devices, such as smart phones and mobile robots. This talk presents an overview of this emerging area. We will also discuss some ongoing work in our group, where we focus on optimizing CNN inference via custom FPGA-based accelerators or mobile graphics processing units (mobile GPUs).

Dr. Soheil Ghiasi is a professor of electrical and computer engineering at the University of California, Davis. His research interests are design and optimization of embedded systems for signal processing, machine learning and multimedia applications. He received his B.S. degree from Sharif University of Technology, Tehran, Iran in 1998, and his M.S. and Ph.D. in Computer Science from University of California, Los Angeles in 2002 and 2004, respectively. He has served on the organizing and technical program committees of numerous technical conferences, and several journals in the general area of computing systems. He is a senior member of IEEE and ACM.