Select a calendar:
Filter September Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for September
-
CS Colloquium: Ian Goodfellow (Google) - Generative Adversarial Networks
Tue, Sep 05, 2017 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ian Goodfellow, Google
Talk Title: Generative Adversarial Networks
Series: NVIDIA Distinguished Lecture Series in Machine Learning
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium.
Generative adversarial networks (GANs) are machine learning models that are able to imagine new data, such as images, given a set of training data. They solve difficult approximate probabilistic computations using game theory. A generator network competes to fool a discriminator network in a game whose Nash equilibrium corresponds to recovering the probability distribution that generated the training data. GANs open many possibilities for machine learning algorithms.
Rather than associating input values in the training set with specific output values, GANs are able to learn to evaluate whether a particular output was one of many potential acceptable outputs or not.
Part of NVIDIA Distinguished Lecture Series in Machine Learning.
Biography: Ian Goodfellow (PhD in machine learning, University of Montreal, 2014) is a research scientist at Google. His research interests include most deep learning topics, especially generative models and machine learning security and privacy. He invented generative adversarial networks, was an influential early researcher studying adversarial examples, and is the lead author of the MIT Press textbook Deep Learning (www.deeplearningbook.org). He runs the Self-Organizing Conference on Machine Learning, which was founded at OpenAI in 2016.
Host: Yan Liu
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CAIS Seminar: Drs. Milind Tambe & Eric Rice (University of Southern California) - AI for Social Good
Thu, Sep 07, 2017 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Milind Tambe & Dr. Eric Rice, University of Southern California
Talk Title: AI for Social Good
Series: Center for AI in Society (CAIS) Seminar Series
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium
How can AI be used for social good? Artificial intelligence has received an enormous amount of attention in the popular press over the past few years. Much of this press is negative, focusing on job loss due to automation or fears of weaponized AI. In this lecture, Drs. Tambe and Rice will share their vision for how AI and social work can come together in the 21st century to tackle some of the world's most vexing social issues. They will discuss how they created the USC Center for Artificial Intelligence in Society and its mission; and will share some of CAIS main areas of research, including homelessness, suicide prevention, substance abuse prevention, gang violence prevention, wildlife conservation, and counter-terrorism.
Biography: Drs. Milind Tambe and Eric Rice are the co-directors and co-founders of USC CAIS. Dr. Tambe is the Helen N. and Emmett H. Jones Professor in Viterbi School of Engineering and Dr. Rice is an associate professor in the Suzanne Dworak-Peck School of Social Work.
Host: Milind Tambe
Location: Seeley Wintersmith Mudd Memorial Hall (of Philosophy) (MHP) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CAIS Seminar: Dr. David Traum (University of Southern California) - Conversations with History: The New Dimensions in Testimony Project
Thu, Sep 14, 2017 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. David Traum, University of Southern California
Talk Title: Conversations with History: The New Dimensions in Testimony Project
Series: Center for AI in Society (CAIS) Seminar Series
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium
One of the best and most engaging methods of learning about history, and particularly implications for future behavior, is direct conversation with those who can give a first person account. The USC Institute for Creative Technologies (ICT) has developed "time-offset interaction" technology to allow interactive conversations with recordings of an eyewitness to history, so that much of this experience can be had without the synchronous participation of the subject. I will describe and demo the use of this technology in the New Dimensions in Testimony project - a collaboration with the USC Shoah Foundation and Conscience Display, in which people can interact with Holocaust survivors in this manner. Time permitting, I will also present its use in a similar project to increase awareness of the consequences of sexual assault in the military.
Biography: David Traum is the Director for Natural Language Research at the USC Institute for Creative Technologies and a research faculty member of the Department of Computer Science at USC. He leads the Natural Language Dialogue Group at ICT; his research focus is on interactive dialogue between humans and machines.
Host: Milind Tambe
Location: Seeley Wintersmith Mudd Memorial Hall (of Philosophy) (MHP) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Julian McAuley (UCSD) - Structured Output Models of Recommendations, Activities, and Behavior
Tue, Sep 19, 2017 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Julian McAuley, University of California, San Diego
Talk Title: Structured Output Models of Recommendations, Activities, and Behavior
Series: Visa Research Machine Learning Seminar Series hosted by USC Machine Learning Center
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium.
Predictive models of human behavior--and in particular recommender systems--learn patterns from large volumes of historical activity data, in order to make personalized predictions that adapt to the needs, nuances, and preferences of individuals. Models may take incredibly complex data as *input*, ranging from text, images, social networks, or sequence data. However, the *outputs* they are trained to predict--clicks, purchases, transactions, etc.--are typically simple, numerical quantities, in order for the problem to be cast in terms of traditional supervised learning frameworks.
In this talk, we discuss possible extensions to such personalized, predictive models of human behavior so that they are capable of predicting complex structured *outputs*. For example, rather than training a model to predict what content a user might interact with, we could predict how they would react to unseen content, in the form of text they might write. Or, rather than predicting whether a user would purchase an existing product, we could predict the characteristics or attributes of the types of products that *should* be created.
Biography: Julian McAuley has been an Assistant Professor in the Computer Science Department at the University of California, San Diego since 2014. Previously he was a postdoctoral scholar at Stanford University after receiving his PhD from the Australian National University in 2011. His research is concerned with developing predictive models of human behavior using large volumes of online activity data.
Host: Yan Liu
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Dr. Kris Zacny (Honeybee Robotics) - Honeybee Robotics
Thu, Sep 21, 2017 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Kris Zacny, PhD, Honeybee Robotics Spacecraft Mechanisms Corporation
Talk Title: Honeybee Robotics
Series: CS Colloquium
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.
Honeybee Robotics, based in Pasadena, develops cutting edge robotic systems for solar system destinations such as the Moon, Mars, Venus, and comets. We are currently operating our hardware on the surface of Mars. Our technologies are also used for Oil & Gas, mining, and U.S. Special Forces.
The presentation will initially provide some background to space exploration and then introduce several exciting missions in the works. These include Lunar Resource Prospector with a goal of identifying volatiles at the lunar South Pole, Mars2020 mission with a goal of returning samples from Mars, Europa deep drill mission with a purpose of penetrating through >10 km thick ice crust and reaching subglacial ice, as well as Planetary Volatiles Extractor with a goal of mining the Moon and Mars.
We will also discuss various ways USC faculty and students could collaborate with Honeybee Robotics. Our company currently employs several USC alumni as well as interns, and works with USC professors on space technologies.
Biography: Dr. Kris Zacny is Vice President and Director of Exploration Technology Group at Honeybee Robotics in Pasadena. His expertise includes terrestrial and extraterrestrial robotic drilling, excavation, sample handling and processing, geotechnical systems, and sensors.
In his previous capacity as an engineer in the South African mining industry, Dr. Zacny managed numerous underground mining projects. Dr. Zacny received his PhD at UC Berkeley in Geotechnical Engineering with an emphasis on Mars drilling, and his ME at UC Berkeley in Petroleum Engineering with emphasis on Drilling and Materials Science. He received his BSc cum laude in Mechanical Engineering at U. Cape Town.
He has participated in several Arctic, Antarctic, Atacama, and Greenland expeditions. Dr. Zacny has over 200 publications related to extreme drilling and excavation and has managed over 100 technology projects. He has over 40 NASA New Technology Records and four NASA Group Achievement Awards.
Host: Computer Science Department
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CAIS Seminar: Dr. Ece Kamar (Microsoft Research) - Directions in Hybrid Intelligence: Discovering Blind Spots of AI
Thu, Sep 21, 2017 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Ece Kamar, Microsoft Research
Talk Title: Directions in Hybrid Intelligence: Discovering Blind Spots of AI
Series: Center for AI in Society (CAIS) Seminar Series
Abstract: Despite advances in AI, machines still have limitations in accomplishing tasks that come naturally to humans. When AI systems are fielded in the open world, these limitations cause concerns around reliability, biases and trust. In this talk, Dr. Kamar will argue that hybrid systems that combine the strengths of machine and human intelligence is key to overcoming the limitations of AI algorithms and developing reliable systems. She will provide an overview of multiple projects, which investigate how to integrate human intelligence into the training, execution and troubleshooting of AI systems.
Biography: Dr. Ece Kamar is a Senior Researcher in the Adaptive Systems and Interaction Group at Microsoft Research. She received her Ph.D. in computer science from Harvard University. Her work spans several subfields of AI, including planning, machine learning, multi-agent systems and human-computer teamwork and is inspired by real-world applications.
Host: Milind Tambe
Location: Seeley Wintersmith Mudd Memorial Hall (of Philosophy) (MHP) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
Probability and Statistics Seminar: Ilya Mironov (Google Brain) - Differential Privacy: From Principled Foundations to Your Browser
Fri, Sep 22, 2017 @ 03:20 PM - 04:30 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ilya Mironov, Google Brain
Talk Title: Differential Privacy: From Principled Foundations to Your Browser
Series: Probability and Statistics Seminar
Abstract: We survey progress in understanding of privacy in statistical databases over the last 10+ years, starting with early negative results followed by emergence of the notion of differential privacy and its variants. In the second half of the talk we cover uses of differential privacy in the Chrome browser, and its recent applications in machine learning tasks such as text and image recognition.
Biography: Ilya Mironov is a Staff Research Scientist in Google Brain. After completing his PhD at Stanford in 2003, he joined Microsoft Research Silicon Valley, where he worked on cryptography, cryptanalysis, and privacy until 2014.
Host: Stanislav Minsker
Location: Kaprielian Hall (KAP) - 414
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Kai-Wei Chang (UCLA) - Structured Predictions: Practical Advancements and Applications in Natural Language Processing
Tue, Sep 26, 2017 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Kai-Wei Chang, University of California, Los Angeles
Talk Title: Structured Predictions: Practical Advancements and Applications in Natural Language Processing
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.
Many machine learning problems involve making joint predictions over a set of mutually dependent output variables. The
dependencies between output variables can be represented by a structure, such as a sequence, a tree, a clustering of nodes, or a graph. Structured prediction models have been proposed for problems of this type, and they have been shown to be successful in many application areas, such as natural language processing, computer vision, and bioinformatics. In this talk, I will describe a collection of results that improve several aspects of these approaches. Our results lead to efficient learning algorithms for structured prediction models, which, in turn, support reduction in problem size, improvements in
training and evaluation speed. I will also discuss potential risks and challenges when using structured prediction models.
Related information is at https://urldefense.proofpoint.com/v2/url?u=http-3A__www.cs.virginia.edu_-7Ekc2wc_talk_sp.html&d=DwIBaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=LW6zU4yKxktEWcUPnmtKow&m=gw-3C-3UJqv9mPCsdDWaZHFxfXoQ6oXlSMsVWGL1xE0&s=l7eOcCL3YxMMSSFD4dVdUUMKTrGVB5Z8Dm0VD1cHVDM&e=
Biography: Kai-Wei Chang is an assistant professor in the Department of Computer Science at the University of California at Los Angeles. He has published broadly in machine learning and natural language processing. His research has mainly focused on designing machine learning methods for handling large and complex data. He has been involved in developing several machine learning libraries, including LIBLINEAR, Vowpal Wabbit, and Illinois-SL. He was an assistant professor at the University of Virginia in 2016-2017. He obtained his Ph.D. from the University of Illinois at Urbana-Champaign in 2015 and was a post-doctoral researcher at Microsoft Research in 2016. Kai-Wei was awarded the KDD Best Paper Award (2010), EMNLP Best Long Paper Award (2017), and the Yahoo! Key Scientific Challenges Award (2011).
Additional information is available at https://urldefense.proofpoint.com/v2/url?u=http-3A__kwchang.net&d=DwIBaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=LW6zU4yKxktEWcUPnmtKow&m=gw-3C-3UJqv9mPCsdDWaZHFxfXoQ6oXlSMsVWGL1xE0&s=wik3X8kutwqg-z2gIVP9M7W-uRkf04mPpX4HhWqxCDM&e=.
Host: Fei Sha
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CCI Seminar: Jimmy Soni – A Mind at Play: How Claude Shannon Invented the Information Age
Wed, Sep 27, 2017 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Jimmy Soni,
Talk Title: A Mind at Play: How Claude Shannon Invented the Information Age
Abstract: Claude Shannon was a groundbreaking polymath, a brilliant tinkerer, and a digital pioneer. He constructed a fleet of customized unicycles and a flamethrowing trumpet, outfoxed Vegas casinos, and built juggling robots. He also wrote the seminal text of the digital revolution, which has been called "the Magna Carta of the Information Age." His discoveries would lead contemporaries to compare him to Albert Einstein and Isaac Newton. His work anticipated by decades the world we'd be living in today-”and gave mathematicians and engineers the tools to bring that world to pass.
In this elegantly written, exhaustively researched biography, Jimmy Soni and Rob Goodman reveal Claude Shannon's full story for the first time. It's the story of a small-town Michigan boy whose career stretched from the era of room-sized computers powered by gears and string to the age of Apple. It's the story of the origins of our digital world in the tunnels of MIT and the "idea factory" of Bell Labs, in the "scientists' war" with Nazi Germany, and in the work of Shannon's collaborators and rivals, thinkers like Alan Turing, John von Neumann, Vannevar Bush, and Norbert Wiener.
And it's the story of Shannon's life as an often reclusive, always playful genius. With access to Shannon's family and friends, A Mind at Play brings this singular innovator and creative genius to life.
Biography: Jimmy Soni was managing editor at The Huffington Post from January 2012-2014. Previously he had worked as a strategy consultant at McKinsey and Company, as well as a speech writer at the office of the Mayor of the District of Columbia. Soni has co-authored several pieces with fellow Duke graduate Rob Goodman; their work has been featured in Politico, The Huffington Post, Business Insider, AdWeek, and The Atlantic, among others.
In 2012, Jimmy, published his first book a biography of Cato the Younger, titled Rome's Last Citizen: The Life and Legacy of Cato, Mortal Enemy of Caesar.
Host: Center for Cyber-Physical Systems and the Internet of Things
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium Event: Facebook Tech Talk
Thu, Sep 28, 2017 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Alex Helm, Catrina Manahan, Charles Kuykendoll, Yuandong Tian, Min Li, Qiachao Que, See Biography
Talk Title: AI in Games: Achievements and Challenges
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.
Recently, substantial progress of AI has been made in applications that require advanced pattern reading, including computer vision, speech recognition and natural language processing. However, it remains an open problem whether AI will make the same level of progress in tasks that require sophisticated reasoning, planning and decision making in complicated game environments similar to the real-world. In this talk, I present the state-of-the-art approaches to build such an AI, our recent contributions in terms of designing more effective algorithms and building extensive and fast general environments, as well as issues and challenges.
Biography: Yuandong Tian is a Research Scientist in Facebook AI Research, working on reasoning with deep learning in games and theoretical analysis of deep non-convex models. He is the leader researcher and engineer for DarkForest (Facebook Computer Go project). Prior to that, he was a Software Engineer/Researcher in Google Self-Driving Car team during 2013-2014. He received Ph.D. in Robotics Institute, Carnegie Mellon University on 2013, Bachelor and Master degree of Computer Science in Shanghai Jiao Tong University. He is the recipient of 2013 ICCV Marr Prize Honorable Mentions for his work on global optimal solution to non-convex optimization in image alignment.
Host: CS Department
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Ryan Rozan
-
CAIS Seminar: Dr. Peng Shi (University of Southern California) - Prediction and Optimization in School Choice
Thu, Sep 28, 2017 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Peng Shi, University of Southern California
Talk Title: Prediction and Optimization in School Choice
Abstract: In public school choice, students submit preference rankings for a given set of schools to the school board, which takes into account everyone's choices to compute the assignment. An important policy lever is what choice options to offer to each neighborhood, and how to prioritize between students. A key trade-off is between giving students equitable chances to go to the schools they want and controlling the city's school busing costs.
We study the optimization problem of choosing the choice menus and priorities for each neighborhood in order to maximize the sum of utilitarian and max-min welfare, subject to capacity and transportation constraints. The optimization is built on top of a predictive model of how students will choose given new choice menus, which we validate using both out-of-sample testing and a field experiment. Under a large market approximation, the optimization reduces to an assortment planning problem in which the objective is social-welfare rather than revenue. We show how to efficiently solve this sub-problem under various discrete choice models, and use this to produce better menus and priorities for Boston, which we evaluate by discrete simulations.
Biography: Dr. Peng Shi is an Assistant Professor of Data Science and Operations at the USC Marshall School of Business. He is interested in developing quantitative methodologies for the betterment of society. His current research focuses on optimization in matching markets, with applications in school choice, public housing, and online marketplaces. His research on school choice won multiple awards, including the ACM SIGecom Doctoral Dissertation Award, the INFORMS Public Sector Operations Best Paper Competition, and the INFORMS Doing Good with Good OR Student Paper Competition. Prior to joining USC, he completed a PhD in Operations Research at MIT, and was a postdoctoral researcher at Microsoft Research.
Host: Milind Tambe
Location: Seeley Wintersmith Mudd Memorial Hall (of Philosophy) (MHP) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
