Skip to content. Skip to navigation
McGill Home SOCS Home
Personal tools
You are here: Home Announcements and Events Seminars Seminar History

Seminar Home
Fall 2015 Schedule
Winter 2016 Schedule
Summer 2016 Schedule

( Fall 2013 )
Category Seminar Info
2013/12/02 Graduate Seminar Series Place: MC103
Time: 12 - 12:30
Speaker: Prof. Benjamin Fung
Affiliation: Associate Professor, McGill School of Information Studies
Title: Applying Data Mining to Real-life Crime Investigation
Abstract: Data mining has demonstrated a lot of success in many domains, from direct marking to bioinformatics. Yet, limited research has been conducted to leverage the power of data mining in real-life crime investigation. In this presentation, I will discuss two data mining methods for crime investigation. The first method aims at identifying the true author of a given anonymous e-mail. The second method is a subject-based search engine that can help investigators to retrieve criminal information from a large collection of textual documents. If time permits, I will also provide an overivew of the ongoing and future research projects in the Data Mining and Security (DMaS) Lab. Biography of Speaker:

Dr. Benjamin Fung is an Associate Professor of Information Studies (SIS) at McGill University and a Research Scientist in the National Cyber-Forensics and Training Alliance Canada (NCFTA Canada). He received a Ph.D. degree in computing science from Simon Fraser University in 2007. Dr. Fung collaborates closely with the national defense, law enforcement, and healthcare sectors. He has over 70 refereed publications that span across the prestigious research forums of data mining, privacy protection, cyber forensics, services computing, and building engineering. His data mining works in crime investigation and authorship analysis have been reported by media worldwide. Before pursuing his academic career, he worked at SAP Business Objects for four years. He is a licensed professional engineer in software engineering. Website:

2013/11/25 Graduate Seminar Series Place: MC103
Time: 12 - 12:30
Speaker: Rahul Garg
Affiliation: SOCS, McGill
Area: compilers
Title: Velociraptor: A compiler toolkit for compiling languages like MATLAB and Python/NumPy to target hybrid CPU+GPU systems
Abstract: Multicore CPUs and accelerators such as general purpose GPUs (GPGPUs) have become mainstream. At the same time, programmers want to use high-level array-based languages such as MATLAB and Python/NumPy. Various language extensions have been proposed for these languages to allow programmers to tap into the power of hybrid CPU/GPU systems. However, language extensions for parallel and hybrid computing require building new compilers or substantially extending existing compilers, and this is a non-trivial task. My toolkit, Velociraptor, is a reusable and portable toolkit that makes it easy to build compilers targeting CPU+GPU systems. I describe the working of my toolkit and will describe how I used it to in two compilers to target multicore CPUs and GPUs. If time permits, I will also show a demo of the compiler generating code for GPUs from Python and/or McVM which is a virtual machine for the MATLAB language developed by other students in my lab.
2013/11/13 Graduate Seminar Series Place: MC103
Time: 12 - 12:30
Speaker: Ladan Mahabadi
Affiliation: McGill SOCS
Title: Music Self-similarity and complexity leveraged for composer classification and computational Turing tests

Music is an information-bearing medium, containing progressions of notes and silences (musical events) ordered in time. Its complexity derives from its information-rich structure, which enables music to be molded to the imagination of any creator, regardless of time or geography. We use the prevalence of patterns and complex structures in music to (1) investigate self-similarity features extracted from musical rhythm, and (2) to create a more secure, user-friendly computational Turing test.

(1) We use similarities hidden in different layers of musical rhythm to construct a concise structural identity (temporal fractal features). This work extends the temporal self-similarity analysis to non-Western music and presents the fractal features in rhythm as a universal feature set. These features are used for longitudinal analysis of compositions in a composer's body of work, and are applied as composer descriptors for classification in two large Western and non-Western music score repertoires. I will present both Western and non-Western composer classification results, which show that fractal features provide complimentary information about the underlying structure that can be used to improve the accuracy of existing classifiers.

(2) The ubiquity of music across all cultures, its complex structure at different layers, and the perceptual characteristics and limitations of the human auditory system are leveraged to construct more accessible, aesthetically pleasing and secure computational Turing tests. Music-based CAPTCHAs, called mCaptchas, are introduced to improve Web accessibility for individuals with visual impairments, to help address and avoid susceptibility to security flaws of existing audio CAPTCHAs, and to improve the overall user experience. I will present empirical evidence of the scheme's security for over 2000 mCaptchas, while its usability is tested by approximately 500 individuals on the Amazon Mechanical Turk (AMT) online market. These results demonstrate that humans can efficiently and accurately solve the generated music-based challenges while sophisticated computer programs fail.

2013/11/06 Graduate Seminar Series Place: MC103
Time: *1:30 - 2*
Speaker: Gayane Petrosyan
Affiliation: McGill, SOCS
Area: Software Engineering/Natural Language Processing
Title: Discovering Information Relevant to API Elements Using Text Classification
Abstract: The number and the size of Application Programming Interfaces (APIs) are continuously growing. Applications become increasingly dependent on APIs. For example, Java SE 6, which is the core of all Java applications, contains 3774 classes and 203 packages. Programmers, both novice and experienced, are faced to the problem of learning about the vast number of APIs. Given the time at their disposal, it is not possible for programmers to learn all the APIs they need in depth. During this seminar I will describe a technique for discovering relevant sections of an API tutorial to help programmers to find additional related information about API elements they are interested in. The suggested technique automatically analyses API tutorials to assess the usefulness of the information contained therein using Natural Language Processing and Text Classification methods. Afterwards, I will present the results of experiments and the lessons learnt from this work.
2013/10/21 Graduate Seminar Series Place: MC103
Time: 12 - 12:30
Speaker: Gheorghe Comanici
Affiliation: McGill, SOCS, Reasoning and Learning Lab
Title: General MDP feature construction using bisimulation
Abstract: We consider the process of generating feature-based representations for Markov Decision Processes (MDPs), a powerful mathematical framework for modelling stochastic sequential decision making. We look at a standard approach for learning good policies in reinforcement learning domains, which involves first the computation of a value function that associates states with expected returns. State features are then used to provide approximation schemes for value function computation. In this talk, I will present a systematic way of generating alternative representations by analyzing behavioural similarities on the set of states (i.e. using bisimulation metrics); I will present theoretical guarantees of corresponding approximation schemes; I will describe its relationship to other pragmatic methods, such as spectral clustering and Bellman Error Basis Functions; lastly, I will discuss its computational tractability.
2013/10/18 Graduate Seminar Series Place: *MC320* (not our usual location MC103)
Time: 12 - 12:30
Speaker: Ouais Alsharif
Affiliation: McGill, SOCS, Reasoning and Learning Lab
Title: End-to-End Text Recognition with Hybrid HMM Maxout Models
Abstract: The problem of detecting and recognizing text in natural scenes has proved to be more challenging than its counterpart in documents, with most of the previous work focusing on a single part of the problem. In this work, we propose new solutions to the character and word recognition problems and then show how to combine these solutions in an end-to-end text-recognition system. We do so by leveraging the recently introduced Maxout networks along with hybrid HMM models that have proven useful for voice recognition. Using these elements, we build a tunable and highly accurate recognition system that beats state-of-the-art results on all the sub-problems for both the ICDAR 2003 and SVT benchmark datasets.
2013/10/11 Vision, Graphics, and Robotics Place: ENGMC 103 (SoCS seminar room)
Time: 10:30 - 11:30
Speaker: James Elder
Affiliation: Center for Vision Research, York University
Area: vision
Title: Perceptual Organization of Shape
Abstract: Humans are very good at rapidly detecting salient objects such as animals in complex natural scenes, and recent psychophysical results suggest that the fastest mechanisms underlying animal detection use contour shape as a principal discriminative cue. How does our visual system extract these contours so rapidly and reliably? While the prevailing computational model represents contours as Markov chains that use only first-order local cues to grouping, computer vision algorithms based on this model fall well below human levels of performance. Here we explore the possibility that the human visual system exploits higher-order shape regularities in order to segment object contours from cluttered scenes. In particular, we consider a recurrent architecture in which higher areas of the object pathway generate shape hypotheses that condition grouping processes in early visual areas. Such a generative model could help to guide local bottom-up grouping mechanisms toward globally consistent solutions. In constructing an appropriate theoretical framework for recurrent shape processing, a central issue is to ensure that shape topology remains invariant under all actions of the feedforward and feedback processes. This can be achieved by a promising new theory of shape representation based upon a family of local image deformations called formlets, shown to outperform alternative contour-based generative shape models on the important problem of visual shape completion. Biography of Speaker:

James Elder received his PhD in Electrical Engineering from McGill University in 1996. He is currently a member of the Centre for Vision Research and a Professor in the Departments of Electrical Engineering and Computer Science and Psychology at York University. Dr. Elder’s research has won a number of awards and honours, including the Premier’s Research Excellence Award and the Young Investigator Award from the Canadian Image Processing and Pattern Recognition Society. His 3DTown research has recently been featured in the National Post and on CBC radio and television.

2013/10/09 Graduate Seminar Series Place: MC103
Time: 12 - 12:30
Speaker: Anqi Xu
Affiliation: McGill CIM
Area: Robotics
Title: Adaptive Parameter EXploration (APEX): Adaptation of Robot Autonomy from Human Participation
Abstract: The problem of Adaptation from Participation (AfP) aims to improve the efficiency of a human-robot team, by adapting the robot’s autonomous behaviors based on input from the human collaborator. We propose a solution, namely the Adaptive Parameter EXploration (APEX) algorithm, that learns from the operator’s intervening commands and dynamically adjusts system parameters of the robot autonomy. We explore this approach within the context of visual navigation, where the human-robot team is tasked to cover and patrol different types of terrain boundaries, such as coastlines and roads. We present empirical evaluations of the APEX solution to AfP, deployed on both an aerial robot within a controlled environment, and a wheeled autonomous vehicle operating within a challenging university campus setting.

YouTube vid link:

2013/10/01 General Place: MC103
Time: 14:30 - 15:30
Speaker: Peter Thiemann
Title: Efficient Access Analysis Using JavaScript Proxies
Abstract: JSConTest introduced the notions of effect monitoring and dynamic effect inference for JavaScript. It enables the description of effects with path specifications resembling regular expressions. It is implemented by an offline source code transformation. To overcome the limitations of the JSConTest implementation, we redesigned and reimplemented effect monitoring by taking advantange of JavaScript proxies. Our new design avoids all drawbacks of the prior implementation. It guarantees full interposition; it is not restricted to a subset of JavaScript; it is self-maintaining; and its scalability to large programs is significantly better than with JSConTest. The improved scalability has two sources. First, the reimplementation is significantly faster than the original, transformation-based implementation. Second, the reimplementation relies on the fly-weight pattern and on trace reduction to conserve memory. Only the combination of these techniques enables monitoring and inference for large programs.
2013/09/24 Vision, Graphics, and Robotics Place: MC437
Time: 14:30 - 15:30
Speaker: Wolfgang Heidrich
Affiliation: University of British Columbia
Title: Light-in-Flight: Transient Imaging using Photonic Mixer Devices
Abstract: Transient imaging is a recent imaging modality in which short pulses of light are observed "in flight" as they propagate through a scene. Transient images are useful to help understand light propagation in complex environments and to analyze light transport for research and many practical applications. Two such examples are the reconstruction of occluded geometry, i.e. "looking around a corner", or measuring surface reflectance. Unfortunately, advances in research and practical applications have so far been hindered by the high cost of the required instrumentation, as well as the fragility and difficulty to operate and calibrate devices such as femtosecond lasers and streak cameras. To address this, we present a device that allows inexpensive and fast transient imaging using photonic mixer devices (PMDs). Our portable device achieves this by capturing a sequence of modulated images with a PMD sensor and inferring a transient image using numerical optimization and a mathematical model for local light interactions. By doing so, the cost of transient imaging is reduced by several orders of magnitude and the capture process is dramatically sped up and simplified. We envision that in the future not only research but virtually everybody has access to inexpensive, fast and portable transient-image cameras with its many emerging applications. Biography of Speaker:

Professor Wolfgang Heidrich holds the Dolby Research Chair in Computer Science at the University of British Columbia. He received a PhD in Computer Science from the University of Erlangen in 1999, and then worked as a Research Associate in the Computer Graphics Group of the Max-Planck-Institute for Computer Science in Saarbrucken, Germany, before joining UBC in 2000. Heidrich's research interests lie at the intersection of computer graphics, computer vision, imaging, and optics. In particular, he has worked on High Dynamic Range imaging and display, image-based modeling, measuring, and rendering, geometry acquisition, GPU-based rendering, and global illumination. Heidrich has written over 100 refereed publications on these subjects and has served on numerous program committees.

2013/09/18 General Place: MC103
Time: 13:00 - 14:00
Speaker: Angel Cuevas Rumin
Affiliation: Universidad Carlos III de Madrid, Spain
Area: Systems
Title: Characterizing User Engagement in Major OSNs
Abstract: On-line Social Networks have irrupted in the society becoming an essential service in our daily lives in only a few years. Currently hundred of millions of people are subscribed to OSNs like Facebook, Twitter or Google+ and use them daily to interact with their surrounding social environment. Under this environment the research community is deeply studying these networks to being able to understand them and exploit their possibilities in different areas such as communication, marketing, media, etc. In this talk, we first describe the evolution of Google+, the youngest OSN among the most popular ones, in its first year. Later, we present a comparative analysis of the three major OSN, i.e. Facebook, Twitter and Google+, in terms of: activity, users reactions to this activity, connectivity and volume of public information. Biography of Speaker:

Dr. Ángel Cuevas received his MSc in Telecommunication Engineering, MSc in Telematics Engineering, and Ph.D. in Telematics Engineering from the Universidad Carlos III de Madrid in 2006, 2007, and 2011 respectively. He is currently a tenure-track Assistant Professor in the Department of Telematics Engineering at Universidad Carlos III de Madrid. Prior to that he was Postdoc researcher at Institut Mines-Telecom, Telecom SudParis from March 2011 until Jan 2013. His research interests focus on On-line Social Networks, P2P Networks, Wireless Sensor Networks and Internet measurements. He is co-author of more than 30 papers in prestigious international journals and conferences such as IEEE/ACM Transactions on Networking, ACM Transactions on Sensor Networks, Elsevier Computer Networks, IEEE Network, IEEE Communications Magazine, WWW, ACM CONEXT, ACM MSWiM, IEEE P2P. He is co-recipient of the Best Paper Award in ACM MSWiM 2010.

2013/09/09 General Place: MC103
Time: 13:00 - 14:00
Speaker: Adrian Paschke
Affiliation: Freie Universitaet Berlin, Germany
Area: Rule Based Systems
Title: Reaction RuleML - Standardize Semantic Reaction Rules
Abstract: RuleML is a family of XML languages whose modular system of schemas permits high-precision (Web) rule interchange. The family's top-level distinction is deliberation rules vs. reaction rules. In this talk I will address the Reaction RuleML subfamily of RuleML. Reaction RuleML is a standardized rule markup/serialization language and semantic interchange format for reaction rules and rule-based event processing. Reaction rules include distributed Complex Event Processing (CEP), Knowledge Representation (KR) calculi, as well as Event-Condition-Action (ECA) rules, Production (CA) rules, and Trigger (EA) rules. Reaction RuleML 1.0 incorporates this reactive spectrum of rules into RuleML employing a system of step-wise extensions of the Deliberation RuleML 1.0 foundation. Biography of Speaker:

Professor Dr. Adrian Paschke is head of the Corporate Semantic Web chair (AG-CSW) at the institute of computer science at the Freie Universitaet Berlin (FUB) in Germany. He is director of RuleML Inc., vice director of the Semantics Technologies Institute Berlin (STI Berlin) and the Berlin Semantic Web Meetup Group. He is active in standardization as steering-committee chair of the RuleML Web Rule Standardization Initiative, co-chair of the Reaction RuleML technical group, founding member of the Event Processing Technology Society (EPTS) and chair of the EPTS Reference Architecture working group, secretary of the OASIS LegalRuleML TC, voting member of OMG and active in the OMG API4KB standardization, member of several W3C groups such as the W3C Rule Interchange Format working group, where he is editor of several W3C Semantic Web standards, and member of OASIS, where he is a contributor to the new LegalRuleML TC. He currently coordinates and leads several nationally and internationally funded research projects such as the BMBF InnoProfile project Corporate Semantic Web (CSW), the Transatlantic BPM Education Network (BPM EduNet), and the BMBF Unternehmen Region project Corporate Smart Content (CSC). He also is project leader of several successful open-source projects such as the Prova, Rule Responder, RBSLA, Reaction RuleML. Adrian was involved in multiple industrial and open-source software development and business engineering projects and has helped to spin-off two successful, awarded companies at Freie Universität Berlin, namely Chariteam UG and Klickfilm UG. He recently was general chair of the 6th ACM International Conference on Distributed Event-Based Systems (DEBS 2012) and the 7th International Web Rule Symposium (RuleML 2013).

2013/08/13 Graduate Seminar Series Place: MC103
Time: 12 - 12:30
Speaker: Jonathan Tremblay
Affiliation: McGill, SOCS
Area: Artificial Intelligence and Digital Games
Title: An Exploration Tool for Predicting Stealthy Behaviour
Abstract: Stealthy movement is an important part of many games in the First Person Shooter (FPS) and Role Playing Games (RPG) genres. Structuring a game level to match stealth goals, however, is difficult, and can depend on subtle and fragile inter-actions between the game space, enemy motion, and other factors. In this talk we will apply a probabilistic path-finding approach to efficiently analyze a 2D space and find stealthy paths. This approach naturally accommodates variation in the level design, numbers and movements of enemies, fields of view, and player start and goal placement. Our design is integrated directly into the Unity 3D game development framework, allowing for interactive and highly dynamic exploration of how different virtual spaces and enemy configurations affect the potential for stealthly movement by players, or other NPCs.