Select a calendar:
Filter April Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for April
-
CS Colloquium: Nicolas Papernot (Pennsylvania State University) - Characterizing the Space of Adversarial Examples in Machine Learning
Tue, Apr 03, 2018 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Nicolas Papernot, Pennsylvania State University
Talk Title: Characterizing the Space of Adversarial Examples in Machine Learning
Series: CS Colloquium
Abstract: There is growing recognition that machine learning (ML) exposes new security and privacy vulnerabilities in software systems, yet the technical community's understanding of the nature and extent of these vulnerabilities remains limited but expanding. In this talk, I explore the threat model space of ML algorithms, and systematically explore the vulnerabilities resulting from the poor generalization of ML models when they are presented with inputs manipulated by adversaries. This characterization of the threat space prompts an investigation of defenses that exploit the lack of reliable confidence estimates for predictions made. In particular, we introduce a promising new approach to defensive measures tailored to the structure of deep learning. Through this research, we expose connections between the resilience of ML to adversaries, model interpretability, and training data privacy.
This lecture satisfies requirements for CSCI 591: Research Colloquium. Please note, due to limited capacity, seats will be first come first serve.
Biography: Nicolas Papernot is a PhD student in Computer Science and Engineering working with Professor Patrick McDaniel at the Pennsylvania State University. His research interests lie at the intersection of computer security, privacy and machine learning. He is supported by a Google PhD Fellowship in Security and received a best paper award at ICLR 2017. He is also the co-author of CleverHans, an open-source library widely adopted in the technical community to benchmark machine learning in adversarial settings. In 2016, he received his M.S. in Computer Science and Engineering from the Pennsylvania State University and his M.S. in Engineering Sciences from the Ecole Centrale de Lyon.
Host: Aleksandra Korolova
Location: Olin Hall of Engineering (OHE) - 100D
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CAIS Seminar: Dr. Paul Rosenbloom (USC) – A Cognitive Architectural Perspective on the Past, Present and Future of AI
Wed, Apr 04, 2018 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Paul Rosenbloom, USC
Talk Title: A Cognitive Architectural Perspective on the Past, Present and Future of AI
Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series
Abstract: In this talk Dr. Rosenbloom will briefly introduce and explore the notion of a cognitive architecture, as a hypothesis about the fixed structures that define a mind and yield intelligent behavior when combined with knowledge and skills, and then step back to discuss the current AI era, the history of AI (in terms of past eras), and some of what is coming. He will also touch on a selection of both social and ethical issues with respect to AI.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Dr. Paul Rosenbloom is a Professor of Computer Science at USC and Director for Cognitive Architecture Research at USC's Institute for Creative Technologies. His research concentrates on cognitive architecture-“ integrated models of the fixed structures underlying minds-“and on understanding the nature, structure and stature of computing as a scientific domain and its overlap with the other domains of human study. He is a Fellow of the Association for the Advancement of Artificial Intelligence, the Association for the Advancement of Science, and the Cognitive Science Society.
Host: Milind Tambe
Location: Seeley Wintersmith Mudd Memorial Hall (of Philosophy) (MHP) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Tim Althoff (Stanford University) – Data Science for Human Well-being
Mon, Apr 09, 2018 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Tim Althoff, Stanford University
Talk Title: Data Science for Human Well-being
Series: Computer Science Colloquium
Abstract: The popularity of wearable and mobile devices, including smartphones and smartwatches, has generated an explosion of detailed behavioral data. These massive digital traces provides us with an unparalleled opportunity to realize new types of scientific approaches that provide novel insights about our lives, health, and happiness. However, gaining valuable insights from these data requires new computational approaches that turn observational, scientifically 'weak' data into strong scientific results and can computationally test domain theories at scale.
In this talk, I will describe novel computational methods that leverage digital activity traces at the scale of billions of actions taken by millions of people. These methods combine insights from data mining, social network analysis, and natural language processing to generate actionable insights about our physical and mental well-being. Specifically, I will describe how massive digital activity traces reveal unknown health inequality around the world, and how personalized predictive models can target personalized interventions to combat this inequality. I will demonstrate that modelling how fast we are using search engines enables new types of insights into sleep and cognitive performance. Further, I will describe how natural language processing methods can help improve counseling services for millions of people in crisis.
I will conclude the talk by sketching interesting future directions for computational approaches that leverage digital activity traces to better understand and improve human well-being.
This lecture satisfies requirements for CSCI 591: Research Colloquium. Please note, due to limited capacity in RTH 109, seats will be first come first serve.
Biography: Tim Althoff is a Ph.D. candidate in Computer Science in the Infolab at Stanford University, advised by Jure Leskovec. His research advances computational methods to improve human well-being, combining techniques from Data Mining, Social Network Analysis, and Natural Language Processing. Prior to his PhD, Tim obtained M.S. and B.S. degrees from Stanford University and University of Kaiserslautern, Germany. He has received several fellowships and awards including the SAP Stanford Graduate Fellowship, Fulbright scholarship, German Academic Exchange Service scholarship, the German National Merit Foundation scholarship, and a Best Paper Award by the International Medical Informatics Association. Tim's research has been covered internationally by news outlets including BBC, CNN, The Economist, The Wall Street Journal, and The New York Times.
Host: Computer Science Department
Location: Ronald Tutor Hall of Engineering (RTH) - 109
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: He He (Stanford University) - Learning Interactive Agents
Mon, Apr 09, 2018 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: He He, Stanford University
Talk Title: Learning Interactive Agents
Series: CS Colloquium
Abstract: AI has made huge advancement into our daily life and increasingly we require intelligent agents that work intimately with people in a changing environment. However, current systems mostly work in a passive mode: waiting for requests from users and processing them one at a time. An interactive agent must handle real-time, sequential inputs and actively collaborate with people through communication. In this talk, I will present my recent work addressing challenges in real-time language processing and collaborative dialogue. The first part involves making predictions with incremental inputs. I will focus on the application of simultaneous machine interpretation and show how we can produce both accurate and prompt translations. Then, I will present my work on building agents that collaborate with people through goal-oriented conversation. I will conclude by discussing future directions towards adaptive, active agents.
This lecture satisfies requirements for CSCI 591: Research Colloquium. Please note, due to limited capacity, seats will be first come first serve.
Biography: He He is a postdoctoral researcher at Stanford University. She earned her Ph.D. in Computer Science at the University of Maryland, College Park. She is interested in natural language processing and machine learning. Her research focuses on building intelligent agents that work in a changing environment and interact with people, with an emphasis on language-related problems. Specific applications include dependency parsing, simultaneous machine interpretation, and goal-oriented dialogue. She is the recipient of the 2016 Larry S. Davis doctoral dissertation award.
Host: Fei Sha
Location: Ronald Tutor Hall of Engineering (RTH) - 115
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Neha Kumar (Georgia Institute of Technology) - Solidarity Through Design: Across Borders and Intersections
Tue, Apr 10, 2018 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Neha Kumar, Georgia Institute of Technology
Talk Title: Solidarity Through Design: Across Borders and Intersections
Series: CS Colloquium
Abstract: The field of human-computer interaction is increasingly engaging in technology design targeting underserved contexts, both across and beyond the global south. Populations in these parts may be socioeconomically disadvantaged, impacted by patriarchy, infrastructurally challenged, discriminated on account of caste or class, or all of the above. Dominant discourse considers access to mobile technologies a key asset for addressing these multiple forms of marginalization. However, there may be other assets as well---such as the presence of care, extensive social ties, or resilient sensibilities---that my work examines and leverages.
In my talk, I will present research conducted in three key areas of global development---access, health, and education---to discuss how we might engage in culturally relevant and appropriate technology design for populations across borders and intersections. Taking place in similar but different contexts across India, Cuba, and the United States, these projects highlight how lessons from one context might inform design in another.
This lecture satisfies requirements for CSCI 591: Research Colloquium. Please note, due to limited capacity, seats will be first come first serve.
Biography: Neha Kumar is an assistant professor at the Georgia Institute of Technology. Her research lies at the intersection of human-centered computing and global development. She received her Ph.D. from the School of Information at UC Berkeley in 2013. Before starting at Georgia Tech in 2015, she completed two postdoctoral assignments---the first at University of Washington's Computer Science and Engineering department and the second at the University of Southern California's Annenberg School of Communication. She also holds two Master's degrees from Stanford University---in Computer Science and Learning, Design and Technology. Neha's research publications have received multiple awards at major conferences. She is an inaugural member of the ACM Future of Computing Academy. She received the Lockheed Inspirational Young Faculty award from Georgia Tech's College of Computing in 2017. She was also a recipient of Google's Anita Borg Scholarship and a Facebook Fellowships Finalist in 2012.
Host: Bistra Dilkina
Location: 100D
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CAIS Seminar: Dr. Edward Kaplan (Yale) – Adventures in Policy Modeling!
Wed, Apr 11, 2018 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Edward Kaplan, Yale
Talk Title: Adventures in Policy Modeling!
Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series
Abstract: Policy Modeling refers to the application of operations research, statistics, and other quantitative methods to model policy problems. Recognizing that analyses of all sorts often exhibit diminishing returns in insight to effort, the hope is to capture key features of various policy issues with relatively simple 'first-strike' models. Problem selection and formulation thus compete with the mathematics of solution methods in determining successful applications: where do good problems come from? How can analysts tell if a particular issue is worth pursuing? In addressing these questions, Dr. Kaplan will review some personal adventures in policy modeling selected from public housing, HIV/AIDS prevention, bioterror preparedness, suicide bombings and counterterrorism, in vitro fertilization, predicting presidential elections, and sports.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Dr. Edward H. Kaplan is the William N. and Marie A. Beach Professor of Operations Research, Public Health, and Engineering at Yale. An elected member of both the National Academies of Engineering and Medicine, his research in HIV prevention and counterterrorism has been recognized with the Lanchester Prize, the Edelman Award, and numerous other awards in operations research and public health. Dr. Kaplan was the President of the Institute for Operations Research and the Management Sciences (INFORMS) during 2016, where he preferred the title 'Member in Chief.'
Host: Milind Tambe
Location: Seeley G. Mudd Building (SGM) - 123
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Mikael Henaff (New York University) - Learning Models of the Environment for Sample-Efficient Planning
Thu, Apr 12, 2018 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Mikael Henaff, New York University
Talk Title: Learning Models of the Environment for Sample-Efficient Planning
Series: CS Colloquium
Abstract: Learning to predict how an environment will evolve and the consequences of one's actions is an important ability for autonomous agents, and can enable planning with relatively few interactions with the environment which may be slow or costly. However, learning an accurate predictive model is made difficult due to several challenges, such as partial observability, long-term dependencies and inherent uncertainty in the environment. In this talk, I will present my work on architectures designed to address some of these challenges, as well as work focused on better understanding recurrent network memory over long timescales. I will then present some recent work applying learned environment models for planning, using a simple gradient-based approach which can be used in both discrete and continuous action spaces. This approach is able to match or outperform model-free methods while requiring fewer environment interactions and still enabling real-time performance.
This lecture satisfies requirements for CSCI 591: Research Colloquium. Please note, due to limited capacity, seats will be first come first serve.
Biography: Mikael Henaff is a fifth-year PhD student in computer science at New York University, advised by Yann LeCun. His current research interests are centered around learning predictive models of the environment, model-based reinforcement learning and memory-augmented neural networks. Prior to his Ph.D studies, he worked at the NYU Langone Medical Center and has interned several times at Facebook AI Research. He holds a B.S in mathematics from the University of Texas at Austin and an M.S in mathematics from New York University.
Host: Fei Sha
Location: Olin Hall of Engineering (OHE) - 100D
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Srivatsan Ravi (ISI USC) - Synchronization using Transactions: Lower bounds and Algorithms
Mon, Apr 16, 2018 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Srivatsan Ravi, ISI USC
Talk Title: Synchronization using Transactions: Lower bounds and Algorithms
Series: CS Colloquium
Abstract: Designing algorithms to exploit today's distributed computing platforms ranging
from general-purpose multicore CPUs, cloud infrastructures to domain-specific decentralized computing systems emphasizes the need for designing robust and fault-tolerant synchronization protocols. However, traditional techniques for synchronization are either too coarse-grained to exploit concurrency or require application-specific fine-grained synchronization.
The Transactional Memory (TM) abstraction is a synchronization mechanism
for multicore programming proposed as a middle ground: it intends to combine an easy-to-use programming model with an efficient utilization of hardware concurrency. TM allows the programmer to speculatively execute sequences of shared-memory operations as atomic in-memory transactions with safe semantics: state witnessed by each transaction is consistent with some sequential execution. Thus, the programmer can design applications having largely sequential semantics in mind and let TM take care, at run-time, of dealing with problems associated with process asynchrony and adversarial failures.
In this talk, we focus on a model for hybrid TMs that exploits hardware extensions in prevalent CPU architectures to support small transactions. We present lower bound proof constructions for implementing safe hybrid transactions and its implications for the complexity of concurrent data structures. We conclude by outlining how transactions as a synchronization mechanism can serve as highly robust universal constructions for domain-specific distributed computing models.
This lecture satisfies requirements for CSCI 591: Research Colloquium. Please note, due to limited capacity, seats will be first come first serve.
Biography: Srivatsan Ravi is a computer scientist at the Information Sciences Institute in University of Southern California (USC). His research interests are centered around the theory and practice of distributed computing. Specifically, he works on algorithms and lower bounds for fault-tolerant distributed systems. His research is motivated by emerging new hardware trends that require a new abstract computation model or via introduction of distributed computing techniques to domains where the sequential implementation continues to be state-of-the-art.
He received his Ph.D. degree from Technical University of Berlin in Germany, where he received the Marie Curie Ph.D. Fellowship and was a member of Deutsche-Telekom Labs, Berlin. His Masters degree is from Cornell University, U.S.A and his Bachelors degree is from Anna University, India.
Host: John Heidemann
Location: Ronald Tutor Hall of Engineering (RTH) - 115
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CAIS Seminar: Dr. Vipin Kumar (University of Minnesota) – Big Data in Climate and Earth Sciences: Challenges and Opportunities for Machine Learning
Thu, Apr 19, 2018 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Vipin Kumar, University of Minnesota
Talk Title: Big Data in Climate and Earth Sciences: Challenges and Opportunities for Machine Learning
Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series
Abstract: A massive amount of data about Earth and its environment is continuously being generated by a large number of Earth observing satellites as well as physics-based earth system models running on large-scale computational platforms. These datasets offer huge potential for understanding how the Earth's climate and ecosystem have been changing and how they are being impacted by humans' actions. This talk will discuss various challenges involved in analyzing these massive datasets as well as opportunities they present for both advancing machine learning as well as the science of climate change in the context of monitoring the state of the tropical forests and surface water on a global scale.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Dr. Vipin Kumar is a Regents Professor and holds William Norris Chair in the department of Computer Science and Engineering at the University of Minnesota. His research interests include data mining, high-performance computing, and their applications in climate/ecosystems and health care. He is currently leading an NSF Expedition project on understanding climate change using data science approaches.
Host: Milind Tambe
Location: Mark Taper Hall Of Humanities (THH) - 301
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CCI Seminar: Karan Motwani (Starbucks Coffee Company) – Developing Blockchain Solutions Beyond Cryptocurrency
Thu, Apr 26, 2018 @ 02:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Karan Motwani, Starbucks Coffee Company
Talk Title: Developing Blockchain Solutions Beyond Cryptocurrency
Series: USC Center for Cyber-Physical Systems and the Internet of Things Seminar Series
Abstract: Talk will cover:
- Fundamentals of Blockchain -“ highlights key differences between few Blockchain platforms.
- Considerations when developing Blockchain solutions with emphasis on Ethereum
- Components required to deploy a fully functioning Blockchain solution
- Evaluating use cases which can benefit from Blockchain implementation
- Challenges around Blockchain technology and its future ahead.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Karan Motwani is an IT Leader with 17+ years of experience in consulting, architecture, engineering, and strategic leadership roles. He has worked with companies from Europe, Latin America, Asia, Middle East and the United States on supply chain and finance solutions. From this experience, he brings an entrepreneurial perspective, and an ability to work across business and engineering on Blockchain application to Supply chain and Finance scenarios.
Host: Bhaskar Krishnamachari
Location: Michelson Center for Convergent Bioscience (MCB) - Michelson Building (MCB) 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
