Select a calendar:
Filter May Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for May 04, 2018
-
: Building Safe and Secure Cyber-Physical Systems Against All Odds
Fri, May 04, 2018 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Radoslav Ivanov, University of Pennsylvania
Talk Title: Building Safe and Secure Cyber-Physical Systems Against All Odds
Series: Center for Cyber-Physical Systems and Internet of Things
Abstract: The increased autonomy of modern Cyber-Physical Systems (CPS) has exposed our limited understanding of systems of such complexity. Multiple deadly accidents in different domains (e.g., automotive, medical, aircraft) have occurred in the last several years, some due to partially known and changing (physiological) models and some due to malicious attacks that disrupt the system operation. In this talk, I will discuss my work on ensuring the safety and security of modern CPS; in particular, my focus is on providing accurate information with guarantees as a necessary condition to closing the loop. In the Medical CPS domain, I have developed parameter-invariant and context-aware detection and estimation approaches with guaranteed performance regardless of the values of unknown patient-specific physiological parameters (e.g., metabolic rate). We have successfully applied these approaches on real-patient data from the Children's Hospital of Philadelphia for the purpose of monitoring the patient's oxygen content during surgery.
In the CPS security domain, my work makes use of the inherent sensor redundancy available in modern CPS in order to argue about the system safety and security even when some components might be under attack. In particular, I have proposed attack-resilient sensor fusion techniques that do not require any assumptions about which particular sensors fail or are under attack in order to detect safety-critical states. We have evaluated the benefit of sensor fusion in a number of automotive CPS applications where the system has access to multiple sensors that can be used to estimate the same state (e.g., velocity can be estimated using encoders, cameras, GPS, etc.).
Biography: Radoslav Ivanov received the B.A. degree in computer science and economics from Colgate University, NY, and the Ph.D. degree in computer and information science from the University of Pennsylvania. He is currently a postdoctoral researcher at the University of Pennsylvania, working with Insup Lee and James Weimer. Radoslav's research interests include the design and control of safe and secure cyber-physical systems, in particular, automotive and medical CPS, and predictive and retrospective analysis of medical patient data.
Host: Professor Paul Bogdan
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Talyia White
-
NL Seminar-Neural Creative Language Generation PhD Defense Practice Talk
Fri, May 04, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Marjan Ghazvininejad , USC/ISI
Talk Title: Neural Creative Language Generation PhD Defense Practice Talk
Series: Natural Language Seminar
Abstract: Natural language generation is a well studied and still very challenging field in natural language processing. One of the less studied NLG tasks is the generation of creative texts such as jokes, puns, or poems. Multiple reasons contribute to the difficulty of research in this area. First, no immediate application exists for creative language generation. This has made the research on creative NLG extremely diverse, having different goals, assumptions, and constraints. Second, no quantitative measure exists for creative NLG tasks. Consequently, it is often difficult to tune the parameters of creative generation models and drive improvements to these systems. Lack of a quantitative metric and the absence of a well-defined immediate application makes comparing different methods and finding the state of the art an almost impossible task in this area. Finally, rule-based systems for creative language generation are not yet combined with deep learning methods. Rule based systems are powerful in capturing human knowledge, but it is often too time-consuming to present all the required knowledge in rules. On the other hand, deep learning models can automatically extract knowledge from the data, but they often miss out some essential knowledge that can be easily captured in rule based systems.
In this work, we address these challenges for poetry generation, which is one of the main areas of creative language generation. We introduce password poems as a new application for poetry generation. These passwords are highly secure, and we show that they are easier to recall and preferable compared to passwords created by other methods that guarantee the same level of security. Furthermore, we combine finite state machinery with deep learning models in a system for generating poems for any given topic. We introduce a quantitative metric for evaluating the generated poems and build the first interactive poetry generation system that enables users to revise system generated poems by adjusting style configuration settings like alliteration, concreteness and the sentiment of the poem. The system interface also allows users to rate the quality of the poem. We collect users rating for poems with various style settings and use them to automatically tune the system style parameters. In order to improve the coherence of generated poems, we introduce a method to borrow ideas from existing human literature and build a poetry translation system. We study how poetry translation is different from translation of noncreative texts by measuring the language variation added during the translation process. We show that humans translate poems much more freely compared to general texts. Based on this observation, we build a machine translation system specifically for translating poetry which uses language variation in the translation process to generate rhythmic and rhyming translations.
Biography: Marjan Ghazvininejad is a Ph.D. student at ISI working with Professor Kevin Knight
Host: Nanyun Peng
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
