Skip to content

2017-18

Fall 2017

Aug. 25

Introduction to EECS 290, Mukesh Singhal, UC Merced

Sept. 15

Scalable Asynchronous Gradient Descent Optimization for Big Models, Torres Martin, UC Merced

Abstract

The number of features in models has been steadily growing and it is now common to see models with millions or even billions of features. However, existing data analytics systems approach predictive model training exclusively from a data-parallel perspective by partitioning the data to multiple workers and executing computations concurrently over different partitions. Although various synchronization policies are used to emphasize speedup or convergence, there is little attention on model management and its importance for effective training. In this work, we present a general framework for parallelizing stochastic optimization algorithms over massive models that cannot fit in memory by vertically partitioning the model offline and asynchronously updating the resulting partitions online. We identify suboptimal behavior in the naive implementation and minimize concurrent requests to the common model by introducing a preemptive push-based sharing mechanism. Our experimental results show improved convergence over HOGWILD! for both real and synthetic datasets and is the only solution scalable to massive models. .

Biography

Martin Torres is a PhD student in the EECS graduate group at UC Merced, working with Prof. Florin Rusu. He received his BS in Computer Science and Cognitive Science from California State University Stanislaus. His research includes large-scale data analytics, focusing on optimizing various machine learning algorithms across different architectures and systems. .

Sept. 22

Urban Impervious Surface Extraction Using High-Resolution Remote Sensing Images, Dr. Zhenfeng Shao, State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University

Abstract

Impervious surfaces are anthropogenic features through which water cannot infiltrate into the soil. Impervious surface is a significant indicator of the degree of urbanization and the quality of the urban eco-environment. The rapid development of urbanization brings massive expansion of impervious surfaces, influencing the regional eco-environment and restricting regional sustainable development.

This talk will focus on methods for urban impervious surface extraction from high resolution remote sensing images. An object-oriented framework is proposed. Buffalo in America and other cities in China are selected as case study areas. Various high-resolution images including IKNOS, GeoEye, GF-1, GF-2, ZY3 and other mapping satellites are used. The challenges and future work such as impervious surfaces dynamic monitoring will be discussed.

Biography

Zhenfeng Shao, a full Professor at Wuhan University, China, received the Ph.D. degree in photogrammetry and remote sensing from Wuhan University, China, in 2004, working with the State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS). He has published more than 40 peer-reviewed articles in international journals. His research interests include high-resolution image processing and remote sensing applications.

Dr. Shao was a recipient of the Talbert Abrams Award for the Best Paper in Image Matching from the American Society for Photogrammetry and Remote Sensing in 2014, and the New Century Excellent Talents in University from the Ministry of Education of China in 2012.

Oct. 06

Learning Binary Hash Functions: Optimisation- and Ensemble-based Approaches, Ramin Raziperchikolaei, UC Merced

Abstract

An attractive approach for fast search in image databases is binary hashing, where a hash function maps each high-dimensional, real-valued image onto a low-dimensional, binary vector. The search for similar images is done in the binary space, which is much faster because of using hardware operations to compute the Hamming distances. But, the binary hashing introduces error, which means that images that were originally similar in the real space may not be similar anymore in the binary space. The main goal of the binary hashing is to reduce this error as much as possible by learning hash functions that map dis/similar images onto dis/similar binary codes. In this talk, I will describe our work on finding better ways to learn hash functions. In the first part of my talk, I will focus on the optimisation-based approaches. In this approach, a complicated objective function is defined over the parameters of the hash function. Optimising this nonconvex and nonsmooth objective function is difficult because the output of the hash function is binary. The previous hashing papers ignore the binary constraints and use ad-hoc methods in solving the problem. In our work, we use the "method of auxiliary coordinates (MAC)" to optimise the objective function correctly, by preserving the binary constraints and learning the binary codes and the hash functions jointly. This better optimisation leads to learning better hash functions, which perform more accurately in the nearest neighbors search. The main difficulty of the optimisation-based approach is that all the single-bit hash functions are coupled inside the objective function, which makes the optimisation slow. In the second part of my presentation, I will talk about our proposed ensemble-based approach, which overcomes the main difficulty of the previous approach. The idea is to learn the single-bit hash functions independently and combine them to achieve the final hash function. We use the ensemble-based techniques to make sure that the hash functions are different. This approach gives us several advantages like simpler optimisation problems, massive parallelization, and better performance in image retrieval. Finally, we show that the diversity-based approaches can get even simpler by guessing the single-bit binary codes of the images.

Biography

Ramin Raziperchikolaei is a PhD candidate in the EECS Department of UC Merced. He received his BS in Computer Engineering in 2010 from Iran University of Science and Technology and MS in Artificial Intelligence in 2012 form Sharif Univeristy of Technology, Iran. Since 2013, he has been working towards his PhD degree in machine learning. His research has been focused on learning binary hash functions for fast image retrieval problems.

Oct. 13

Computational Social Science, Professor Alex Petersen, UC Merced

Abstract

The timely combination of accessible computational tools and data availability have led to advances across a wide range of scientific domains in the digital era. In this way, computational tools & methods represent a scientific ‘commons’ that brings together researchers from different disciplines, facilitating interdisciplinary endeavors and cross-disciplinary career paths. As a result, several new researcher communities have sprouted, (e.g. Quantitative Social Science, Computational Social Science, Data Science, Digital Humanities, etc.) which all occupy and leverage this commons. In this talk I will discuss the ‘data science’ pipeline, which includes identifying data sources; accessing or “scraping” raw data; cleaning, organizing, merging and identifying potential pitfalls in the data; exploring and visualizing the underlying statistics; and finally modeling the data in the context of relevant research questions. I will provide examples of computationally-driven social science from my own research, pertaining to the Science of Science & Innovation, as well as an example of the data science pipeline using the Zillow API that produces longitudinal cross-sectional data on housing prices in several local cities to UC Merced.

Biography

Dr. Petersen is an assistant professor in the Management of Complex Ststems unit at UC Merced. His research combines perspectives and methods from statistical physics, network science, computational social science, and economometrics, in order to model science and innovation processes that occur across multiple scales: from individual publications and careers to national innovation systems.

Oct. 20

Optimizing Memory Efficiency for Deep Neural Networks on GPUs, Dr. Chao Li, Qualcomm Research

Abstract

Deep Neural Nets such as Deep Convolutional Networks have achieved state-of-the-art results in various computer vision tasks. Leveraging large training data sets, deep Convolutional Neural Networks (CNNs) evovles to be a deep multi-layer computational structure for high recognition accuracy. Due to the substantial compute and memory operations, however, they require significant execution time. The massive parallel computing capability of GPUs make them as one of the ideal platforms to accelerate CNNs and a number of GPU-based CNN libraries have been developed. While existing works mainly focus on the computational efficiency of CNNs, the memory efficiency of CNNs have been largely overlooked. Yet CNNs have intricate data structures and their memory behavior can have significant impact on the performance. In this talk, I will present our study on optimizing the memory efficiency for DNNs on GPUs. Specifically, we study the memory efficiency of various CNN layers and reveal the performance implication from both data layouts and memory access patterns. Experiments show the universal effect of our proposed optimizations on both single layers and various networks, with up to 27.9x for a single layer and up to 5.6x on the whole networks.

Biography

Chao Li is currently Senior System Engineer (Researcher) in Qualcomm GPU Research Team. His working area lies in computer architecture and programming, especially on exploring new performance features for next-generation GPU systems. He obtained the PhD degree in Computer Engineering at North Carolina State University in 2016. His works have been published in top computer system conferences such as SC, ICS, CGO, PPoPP, ISPASS, etc. He received the ACM/IEEE Supercomputing Conference Best Student Paper Finalist Award in 2016.

Oct. 27

Say Hello to Waymo, Dr. Ioan Sucan Waymo

Abstract

DDriving is integral part of our lives. We do it for fun, but it is more often a necessity. Unfortunately, it is not always safe, and it almost always takes more time than we'd like. Worldwide, 1.2M people die annually on our roadways. In the US alone, we kill 35,000 people a year, the equivalent of a 737 falling out of the sky every working day of the entire year. The vast majority of these accidents involve human error. This makes self-driving technology an enticing promise to greatly improve safety on the road. This talk will provide an overview of Waymo's self-driving technology, with a focus on safety considerations.

Biography

CIoan A. Șucan is currently a Research Software Engineer at Waymo (formerly part of X / Google[x]), working on motion planning for self-driving cars. Before joining Waymo, Dr. Șucan was a Research Scientist at Willow Garage, where he worked on a number of open-source software projects. Dr. Șucan's most well known contributions are MoveIt!, a motion planning and manipulation framework, and the Open Motion Planning Library (OMPL), a software library of sampling-based motion planning algorithms. Dr. Șucan received the Ph.D. and M.S. degrees in computer science from Rice University, Houston TX, in 2011 and 2008, respectively, under the supervision of Prof. Lydia Kavraki. He received the B.S. degree in electrical engineering and computer science from Jacobs University, Bremen, Germany, in 2006.

Nov. 3

Towards Accelerator-Rich Architectures and Systems, Dr. Zhenman Fang Xilinx

Abstract

With Intel's $16.7B acquisition of Altera and the deployment of FPGAs in major cloud service providers including Microsoft and Amazon, we are entering a new era of customized computing. In future architectures and systems, it is anticipated that there will be a sea of heterogeneous accelerators customized for important application domains, such as machine learning and personalized healthcare, to provide better performance and energy-efficiency. Many research problems are still open, such as how to efficiently integrate accelerators into future chips and commodity datacenters, and how to program such accelerator-rich architectures and systems.

In this talk, I will first give a quick overview of my research on accelerator-rich architectures and systems, which spans from application drivers to underlying computer architectures. Then I will present our recent work on CPU-accelerator co-design, where we provide efficient and unified address translation support between CPU cores and accelerators [HPCA 2017 Best Paper Nominee]. It shows that a simple two-level TLB design for accelerators plus the host core MMU for accelerator page walking can be very efficient. On average, it achieves 7.6x speedup over the naïve IOMMU and there is only 6.4% performance gap to the ideal address translation. Third, I will present the concept of accelerators-as-a-service in cloud deployment and introduce our open-source Blaze prototype system [ACM SOCC 2016]. Blaze provides programming and runtime support to enable easy and efficient FPGA accelerator integration into state-of-the-art big data framework Apache Spark. By deploying a PCIe-based FPGA board into each CPU server using Blaze, it can consolidate the cluster size by several folds while providing the same system throughput. Finally, I will talk about some future research that will enhance architecture, programming, compiler, runtime, and security support to accelerator-rich architectures and systems.

Biography

Dr. Zhenman Fang has been a postdoc in UCLA Computer Science Department since July 2014, and recently moved to Xilinx San Jose in mid Sept. During his postdoc, Zhenman worked with Prof. Jason Cong and Prof. Glenn Reinman, and was also a member of two multi-university centers: Center for Domain-Specific Computing (CDSC) and Center for Future Architectures Research (C-FAR). Zhenman received his PhD in June 2014 from Fudan University, China and spent the last 15 months of his PhD program visiting University of Minnesota at Twin Cities.

Zhenman's research lies at the boundary of heterogeneous and energy-efficient computer architectures, big data workloads and systems, and system-level design automation. He has published 10+ papers in top venues that span across computer architecture (HPCA, TACO, ICS), design automation (DAC, ICCAD, FCCM, IEEE Design & Test), and cloud computing (ACM SOCC). Moreover, he also actively serves on the organizing committee and program committee of top conferences including HPCA 2017, ICCD 2017, IISWC 2017, DATE 2018, and ICS 2018. Finally, he has received several awards, including a best paper nominee of HPCA 2017, a best paper award of MEMSYS 2017, a postdoc fellowship from UCLA, a best demo award at the C-FAR center annual review. More details can be found in his personal website: https://sites.google.com/site/fangzhenman/.

Dec. 1

Value Alignment in Artificial Intelligence, Dylan Hadfield-Menell, UC Berkeley

Abstract

I will give an overview of some of the recent work we have been pursuing in formalizing, understanding and solving 'the value alignment problem.' Loosely speaking, this is the problem of ensuring that an AI system's behavior aligns with its designer or users intended objective. This is closely related to the well-studied principal-agent problem from economics, where a firm needs to align an employee's incentives with the firm's ultimate goal. I will present Cooperative Inverse Reinforcement Learning, our initial attempt to mathematically formalize the value alignment problem and discuss the implications of our framework for human robot interaction and robust AI design. .

Biography

I'm a fifth year Ph.D. student at UC Berkeley, advised by Anca Dragan, Pieter Abbeel, and Stuart Russell. My research focuses on the value alignment problem in artificial intelligence. My goal is to design algorithms that learn about and pursue the intended goal of their users, designers, and society in general. My recent work has focused on algorithms for human-robot interaction with unknown preferences and reliability engineering for learning systems.

I'm also interested in work that bridges the gap between AI theory and practical robotics and work on the problem of integrated task and motion planning. Before coming to Berkeley, I did a Master's of Engineering with Leslie Kaelbling and Tomás Lozano-Pérez at MIT. When I'm not working on research I'm usually wrapped up in a Sci-Fi or Fantasy novel, playing ultimate frisbee, or skiing. .

Dec. 8

AuCloud: the Cloud for the Transportation Industry, Dr. Carlos Garcia-Alvarado, Autonomic, Inc.

Spring 2018

Jan. 26

Geographic Knowledge Discovery Using Ground-Level Images and Videos, Professor Shawn Newsam, EECS, UC Merced

Abstract

This work investigates social multimedia for geographic knowledge discovery. Specifically, community-contributed ground-level images and videos are used to map what-is-where on the surface of the Earth in much the same way that overhead images taken from air- or space-borne platforms have been used for decades in the traditional field of remote sensing. The overarching premise is that georeferenced social multimedia data can be considered a form of volunteered geographic information. Further, it can enable geographic discovery not possible through traditional means. The framework, termed proximate sensing, is applied to a range of geographic discovery problems including land cover and land use mapping, mapping public sentiment, mapping pet ownership, and mapping human activities. The image and video analysis is performed using state-of-the-art computer vision techniques based on deep learning.

Biography

Dr. Shawn Newsam is an associate professor and founding faculty in Electrical Engineering and Computer Science at the University of California, Merced. He has degrees from UC Berkeley, UC Davis, and UC Santa Barbara and did a postdoc at Lawrence Livermore National Laboratory before joining UC Merced. He is the recipient of a DOE Early Career Scientist and Engineer Award, an NSF Faculty Early Career Development (CAREER) Award, and a Presidential Early Career Award for Scientists and Engineers (PECASE). His research interests include image processing, computer vision, and machine learning particularly as applied to spatial data.

Feb. 2

Building Internet of Things Systems via Networked Sensing and Mobile Computing Innovations, Professor Wan Du, EECS, UC Merced

Abstract

It is estimated that the global Internet of Things (IoT) system will connect about 30 billion objects and the global market value of IoT will reach $7.1 trillion by 2020. The deployed IoT systems are changing our lives and how we interact with the surrounding world. In this talk, I will introduce my research on building IoT systems via networked sensing and mobile computing innovations. In an interdisciplinary project, we develop a networked sensing system that measures the water quality of urban reservoirs and the spatial wind distribution over the water surface, which in turn enables real-time monitoring and analysis of water quality for smart cities. Three fundamental research problems have been solved. I worked with my colleagues and first found the best locations for wind sensors by studying the correlation of the wind stress at different locations. 10 wind sensors have been deployed in an urban reservoir of Singapore. To collect data from the deployed sensors, we further developed a sparse wireless networking system that provided adaptive communications over long-distance low-power wireless links and efficient data collection over multi-hop paths. To remotely update the software of the deploy sensors or diffuse a bulk of data to them, we designed a fast data dissemination protocol which significantly improved the data dissemination efficiency by transmitting rateless-encoded packets over constructive interference and pipelining. Besides the above academic achievements, the networked sensing system has been providing essential information for Public Utility Board of Singapore to conduct smart reservoir management, which makes the project socially responsible as well. Finally, I will also introduce two mobile computing systems we have developed to enable some interesting IoT applications.

Biography

Dr. Wan Du is currently an Assistant Professor in Electrical Engineering and Computer Science at the University of California, Merced. He had worked as a Research Fellow in the School of Computer Science and Engineering, Nanyang Technological University, Singapore, from 2011 to 2017. Dr. Du has been doing active research on IoT system development, especially networked sensing and mobile computing. His representative research projects include the deployment of a water quality monitoring system in urban reservoirs, visible light communication based on smartphones, smartphone-based activity profiling system, etc. He is also working on two data analytics projects for urban computing. A number of high quality research papers have been published in reputed conferences including ACM MobiCom, ACM SenSys, ACM MobiHoc; ACM/IEEE IPSN; IEEE INFOCOM, IEEE ICDCS; and journals including IEEE/ACM Transactions on Networking, IEEE Transactions on Mobile Computing, IEEE Transactions on Wireless Communications, ACM Transactions on Sensor Networks, etc. His research of water quality monitoring system has received the best paper award in ACM SenSys 2015 and the best demo award in IEEE SECON 2014. He has also received the Distinguished Technical Program Committee (TPC) member award of IEEE INFOCOM 2018.

Feb. 9

For Better or Worse, Richer or Poorer: The Future of Tech for Good, Dr. Brandie Nonnecke, UC Berkeley CITRIS Director of Tech for Social Good
This talk is part of the EECS | CITRIS Frontiers in Technology Series.

Abstract

We have a complicated relationship with tech. Throughout history, technological advancements have helped us address some of our most pressing challenges, but its application has also created new ones. "ATech + Human Love Story" will share examples of how tech--from AI and digital identity systems to social media platforms--can be applied to change our world for good, but also provides caution on how tech must be designed and applied in ways that are inclusive, fair and just.

Biography

Dr. Brandie Nonnecke is the Research & Development Manager for CITRIS, UC Berkeley and Program Director for CITRIS, UC Davis. She is a Fellow at the World Economic Forum where she serves on the Council on the Futureof the Digital Economy and Society. Brandie researches human rights at the intersection of law, policy, and emerging technologies. Her current research is focused on the benefits and risks of AI-enabled decision-making, including issues of fairness, accountability, and appropriate governance structures. She has published research on algorithmic-based decision-making for public service provision in the urban context and outlined recommendations for how to better ensure application of AI to support equity and fairness. She is also researching ethics of biometric-based digital identity systems and recently published a piece highlighting the risks of digital ID systems for refugees.

Feb. 16

The Psychology of Input and Interaction of/with Text and Numbers,Professor Ahmed Sabbir Arif, EECS, UC Merced

Abstract

Text entry has become an essential part of our daily life. Nowadays, we input text and on/with various devices, in both stationary and mobile settings. Since the process of text entry involves both cognitive and motor skills and requires a close cooperation between the system and the user, an understanding of both factors is necessary to develop more efficient input techniques. In this talk, I will discuss the development of a model that accounts for the most important human and system factors to predict text entry performance. I will demonstrate how this model was used to identify and address bottlenecks in text entry performance by making subtle changes in the user interfaces. I will then shift focus to interaction with text end numbers. Data exploration is an integral part of uncovering the secrets and structure of scientific datasets. However, this process is challenging, especially for non-experts who are coming into an expert domain. I will discuss how the common coding theory can be exploited in user interfaces to facilitate collaborative learning, conceptual understanding, and exploration and discovery in different datasets, including gene expressions and metabolic pathways. Finally, I will conclude reflecting on future directions of my research.

Biography

Ahmed Sabbir Arif is an Assistant Professor of Electrical Engineering and Computer Science at UC Merced. As a researcher, his goal is to make computer technologies accessible to everyone by developing intuitive input and interaction techniques. A major thread of his work focuses on smarter solutions for text entry. His other interests include tangible user interfaces, mobile interaction, child-computer interaction, usable security, and data visualization. His research has contributed towards the development of more reliable interactive systems and influenced practices. He has received many prestigious awards for his research, including the Michael A. J. Sweeney Award and the CHISIG Gitte Lindgaard Award. Before joining UC Merced, he was a Postdoctoral Fellow at Ryerson University. He was also an NSERC ENGAGE Postdoctoral Fellow at Flowton Tech and a Research Intern at Microsoft Research, Redmond.

Feb. 23

No seminar

Abstract

No Seminar

Biography

No Seminar.

March 2

Plug-and-play Irrigation Control at Scale, Daniel Winkler, EECS, UC Merced

Abstract

Lawns, also known as turf, cover an estimated 128,000 square kilometers in North America alone, with landscape requirements representing 30% of freshwater consumed in the residential domain. With this consumption comes a large amount of environmental, economic, and social incentive to make turf irrigation systems as efficient as possible. Recent work introduced the concept of distributed control in irrigation systems, but existing control strategies either do not take advantage of the distributed control, or don’t revise the strategy over time in response to collected data. In this work, we introduce PICS, a data-driven control strategy that self-improves over time, adapts to the local specific conditions and weather changes, and requires virtually no human input in both setup and maintenance providing a plug-and-play system that requires minimal pre-deployment efforts. In addition to substantial improvements in ease-of-use, we find across 4 weeks of large-scale irrigation system deployment that PICS improves irrigation system efficiency by 12.0% in comparison to industry best and 3.3% in comparison to academic state-of-the-art. Despite using less water, PICS also was found to improve quality of service by a factor of 4.0x compared to industry best and 2.5x compared to academic state of the art.

Biography

Daniel Winkler received his BS in Computer Science Engineering with honors from UC Merced in 2013. An ACM member, he since has been pursuing his PhD under advisement of Dr. Alberto Cerpa in UC Merced's ANDES Lab. Although his current research focuses on intelligent design and management of turf irrigation systems through the use of embedded devices, Daniel maintains a diverse interest in general resource management applications.

March 9

Simulating virtual crowds with 100,000 agents in real-time on your laptop,Tomer Weiss, CS, UCLA

Abstract

The movement of large numbers of people is important in many situations, such as the evacuation of a building in an emergency, urban planning, and visual effects. Since laboratory experiments are not readily available, most research is conducted by means of computer simulations of crowds. Graphics researchers and others have proposed many simulation models. However, most of these models are tailored for specific scenarios, and are computationally expensive. One of the main challenge stems from the difficulty in leveraging all these into a unified model that scales and works well for both sparse and dense crowds. In this talk, I focus on my recent work in developing a position-based framework for crowd simulation. I demonstrate the framework's strengths by simulating large crowd masses in interactive rates for hundreds of thousands of agents, which was previously unachievable. This new method is suitable for use in interactive games, and was recently presented in the ACM SIGGRAPH conference on Motion in Games 2017, where it received the best paper award.

Biography

Tomer Weiss is a PhD candidate at the University of California Los Angeles, scheduled to defend this thesis in this year. He received the best paper award from the ACM SIGGRAPH conference on motion in games, for his work on virtual crowd simulation. He received his BSc degree in computer science from Tel Aviv University in 2013, and MS in Computer Science from UCLA in 2016. His research interests include computer graphics and optimization methods. He is a member of the UCLA Computer Graphics & Vision Laboratory, directed by Professor Demetri Terzopoulos.

March 16

Autonomous Scooter Design for People with Mobility Challenges,Professor Kaikai Liu, San Jose State University

Abstract

People with mobility challenges, for example, the elderly, blind, and disabled, face a multitude of challenges every day that can prevent them from getting where they want to go. Despite the technical success of existing assistive technologies, for example, electric wheelchairs and scooters, they are still far from effective enough in helping those in need navigate to their destinations in a hassle-free manner. Riders often face challenges operating scooters in certain indoor and crowded places, especially on sidewalks with numerous obstacles and pedestrians. People with certain disabilities, such as the blind, are often unable to drive their scooters. In this talk, we will discuss our ongoing work in designing a cutting-edge autonomous scooter. We focus on indoor navigation scenarios for the autonomous scooter where the current location, maps, and nearby obstacles are unknown. To solve the discrepancies of system complexity, sensor coverage, and resolution, we propose solutions for object mapping and recognition under various spatial and lighting conditions. Solving these challenges will enable the scooter to both travel within buildings and perform tight maneuvers through densely crowded areas automatically. We hope our system will allow people with mobility challenges to ambulate independently and safely in possibly unfamiliar surroundings.

Biography

Kaikai Liu is an assistant professor in the Department of Computer Engineering since August 2015. His research interests include Mobile and Cyber-Physical Systems (CPS), Smart and Intelligent Systems, Internet-of-Things (IoT), Software-Defined Computing and Networking. He has published over 20 peer-reviewed papers in journals and conference proceedings, 1 book, and holds 4 patents (licensed by three companies). He developed several prototype systems from scratch, for example, emergency communication systems for the smart city, Ultra-wideband system for search and rescue victims, indoor localization and navigation. He is a recipient of the Outstanding Achievement Award at UF (four times), the Apple WWDC Scholarship (2013 and 2014), the Innovator Award from the Office of Technology Licensing at UF (2014), the Top Team Award at NSF I-Corps Winter Cohort (Bay area, 2015), the 2015 Gator Engineering Attribute Award for Creativity at UF, IEEE SWC 2017 Best Paper Award, IEEE SECON 2016 Best Paper Award, ACM SenSys 2016 Best Demo - Runner up, 2016 CoE Kordestani Endowed Research Professor, 2017 and 2018 CoE Research Professor Award.

March 23

A Robot Character for Every Home, Mark Palatucci Co-Founder/Head of Cloud AI and Machine Learning at Anki
This talk is part of the EECS | CITRIS Frontiers in Technology Series.

Abstract

For the past several decades, consumer applications of robotics have been more science fiction than reality. However, recent developments in deep-learning, cloud AI, and plummeting prices of both computation and sensing have created the necessary components for a rapidly growing consumer robotics industry to finally emerge. In this talk, I’ll discuss the evolution of Anki from 3 Ph.Ds and a kitchen table prototype, to a global company that has quickly become the 2nd largest producer of consumer robots in the world. I’ll share many of the successes and challenges of producing robots at million+ unit scale, and the important trends that will impact both academia and industry. I’ll talk about the importance of emotion and character for building a great user experience, and some surprising findings about human-robot interaction. I’ll also discuss Anki’s unique “bottom’s up approach" to robotics, and show how with an increasingly complicated series of low-cost mass-market robots, we’ve created a virtuous cycle that’s driving growth in the industry and moving to a future with intelligent, emotive, robot characters for every home.

Biography

Mark Palatucci is the Co-founder and Head of Cloud AI and Machine Learning at Anki. While at Anki, he led the software teams that developed award winning products including Anki Overdrive and Cozmo. He is an inventor on multiple US Patents, and was awarded Ph.D fellowships from the National Science Foundation and Intel Corporation for his research on machine learning. Mark earned a bachelor’s degree in computer science from the University of Pennsylvania and a M.S and Ph.D in Robotics from Carnegie Mellon University.

April 6

An Exciting Future: At the crossroads of people, profit, planet and petabytes of data, Chandrakant Patel Chief Engineering and Senior Fellow, Hewlett-Packard.
This talk is part of the EECS | CITRIS Frontiers in Technology Series.

Abstract

Humanity will face more change over the next 15 years than in all of human history to date. The world will be deeply affected by population increase, shifting resource constraints, rapid urbanization, changing demographics, hyper globalization and sustainability challenges. Moreover, externalities such as environmental pollution, natural disasters and military conflicts will increasingly become a burden to society. In this talk, I will outline the megatrends, and examine the role of future cyber physical systems in addressing these 21st century megatrends. I will seek to drive a vigorous conversation on the role of physical fundamentals and information technologies in instantiating systemic innovations that make life better for everyone. I will close with a perspective on an idea-to-value framework that builds on lessons I have learnt in my career in Silicon Valley.

Biography

Chandrakant is currently the Chief Engineer and Senior Fellow of HP Inc. Chandrakant has led HP Labs in delivering innovations in chips, systems, data centers, storage, networking, print engines and software platforms. He is a pioneer in thermal and energy management in data centers, and in the application of the information technology for available energy management at city scales. Chandrakant is an ASME and an IEEE Fellow, and has been granted 151 patents and published more than150 papers. An advocate of return to fundamentals, he has served as an adjunct faculty in engineering at Chabot College, U.C. Berkeley Extension, San Jose State University and Santa Clara University. In 2014, Chandrakant was elected to the Silicon Valley Engineering Hall of Fame.

April 13

Computational Approaches toward Better Drugs and Better Health Care, Professor Xia Ning Indiana University - Purdue University Indianapolis

Abstract

Drug development and responsible drug use represent critical issues for health care. Drug development has been extremely costly and of extremely low success rate. Even after successful development and FDA approval, many marketed drugs do not introduce equal efficacy on different patients. In this talk, we will present how computational approaches can help accelerate drug development and facilitate precision drug selection. In specific, we will discuss a new ranking framework and ranking methods to prioritize drug candidates when multiple criteria are considered (e.g., drug bioactivity and selectivity). We will also discuss a new ranking-based approach to selecting effective cancer drugs for different patients.

Biography

Xia Ning is an Assistant Professor in the Department of Computer and Information Science (CIS) at the Indiana University – Purdue University Indianapolis (IUPUI). She received her Ph.D. from University of Minnesota, Twin cities, in 2012. From 2012 to 2014, she worked as a research staff member at NEC Labs, America. In Fall 2014, she joined IUPUI. She is also affiliated with the Center for Computational Biology and Bioinformatics (CCBB), Indiana University, and Regenstrief Institute. Ning’s research is on Data Mining, Machine Learning and Big Data analysis with applications on Chemical Informatics, Bioinformatics, Health Informatics and e-commerce, etc., and has been highly interdisciplinary. In specific, Ning’s research focuses on developing scalable models and computational methods to derive knowledge from heterogeneous Big Data, conduct modeling, ranking, classification and prediction, etc., and ultimately solve critical and real high-impact problems. Specific research topics include drug candidate prioritization for drug discovery, cancer drug selection for precision medicine, and information retrieval from electronic medical records.

April 20

Hidden Two-Stream Convolutional Networks for Action Recognition, Yi Zhu, EECS, UC Merced

Abstract

Analyzing videos of human actions involves understanding the temporal relationships among video frames. Convolutional Neural Networks (CNNs) are the current state-of-the-art methods for action recognition in videos. However, the CNN architectures currently being used have difficulty in capturing these relationships. State-of-the-art action recognition approaches rely on traditional local optical flow estimation methods to pre-compute motion information for CNNs. Such a two-stage approach is computationally expensive, storage demanding and not end-to-end trainable.

In this talk, I will first describe the literature and challenges of video classification, and then introduce the motivation of our work. Then I will present a novel CNN architecture that implicitly captures motion information between adjacent frames. This new module can be plugged into any state-of-the-art action recognition framework. We name our approach hidden two-stream CNNs because it takes raw video frames as input and directly predicts action classes without explicitly computing optical flow. We show that our end-to-end approach is 10x faster than a two-stage one, and requires significantly less storage since optical flow does not need to be saved. We present experimental results on four challenging action recognition datasets: UCF101, HMDB51, THUMOS14 and ActivityNet v1.2. Our approach is shown to significantly outperform the previous best real-time approaches.

Biography

Yi Zhu is a PhD student in the EECS program at UC Merced. Since 2014, he has been working with Professor Shawn Newsam towards his PhD degree on computer vision. His research is focused on video action recognition/detection, optical flow/depth estimation and geospatial knowledge discovery.

April 27

Online Partial Throughput Maximization for Multidimensional Coflow, Maryam Shadloo, EECS, UC Merced

Abstract

Coflow has recently been introduced to capture communication patterns that are widely observed in the cloud and massively parallel computing. Coflow consists of a number of flows that each represents data communication from one machine to another. A coflow is completed when all of its flows are completed. Due to its elegant abstraction of the complicated communication processes found in various parallel computing platforms, it has received significant attention. In this talk, we optimize coflow for the objective of maximizing partial throughput. This objective seeks to measure the progress made for partially completed coflows before their deadline. Partially processed coflows still could be useful when their flows send out useful data that can be used for the next round computation. In our measure, a coflow is processed by a certain fraction when all of its flows are processed by the same fraction or more. We consider a natural class of greedy algorithms, which we call myopic concurrent. The algorithms seek to maximize the marginal increase of the partial throughput objective at each time. We analyze the performance of our algorithm against the optimal scheduler. In fact, our result is more general as a flow could be extended to demand various heterogeneous resources. Our experiment demonstrates our algorithm’s superior performance.

Biography

Maryam Shadloo is a PhD student in the EECS program at UC Merced. Since 2014, she has been working in the area of theoretical computer science under the supervision of Prof. Sungjin Im. Specifically, she is interested in designing approximation and online algorithms for algorithmic problems arising in scheduling and resource allocations.

May 4

Optimizing Thread Management on GPUs, Dr. Guoyang Chen, Alibaba Research