Logo: University of Southern California

Events Calendar

Events for May

  • AI Seminar-Centralities, Communities and Dynamics: The Generalized Laplacian Framework

    Fri, May 01, 2015 @ 11:00 AM - 12:00 PM

    Information Sciences Institute

    Conferences, Lectures, & Seminars

    Speaker: Xiaoran Yan , USC/ISI

    Talk Title: Centralities, Communities and Dynamics: The Generalized Laplacian Framework

    Series: Artificial Intelligence Seminar

    Abstract: The interplay between a dynamic process and topology of a network on which it unfolds affects observed network structure. In this talk, we examine the impact of this the interaction on the identification of central nodes and communities in networks. We introduce the generalized Laplacian framework which extends the traditional Laplacian beyond simple diffusion. By mathematically relating dynamic processes to random walks on a transformed network, the generalized Laplacian formulation unifies different measures of centrality and community quality. Thus, a node's centrality describes its participation in the dynamics taking place on the network, and communities are groups of nodes that interact more frequently with each other according to the rules of the dynamic process. We prove that the classic Cheeger's inequality, which relates the spectrum of the Laplacian matrix to the conductance of the best cluster in the network, can be extended to this generalized setting, providing a method for fast graph partitioning under any dynamics. We demonstrate empirically that different dynamic processes lead to divergent views of structure of synthetic and real-world networks.

    Biography: Xiaoran Yan is a Postdoctoral Research Associate at Kristina Lerman's group at ISI-USC. His work focuses on modelling and analyzing dynamics on networks as well as the underlying topological structures. He received a Ph.D. in Computer Science at University of New Mexico.

    Host: Kristina Lerman

    Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=9e22bdf6c8be40a3a5f7abdb6c3fef251

    Location: Information Science Institute (ISI) - 11th Flr. Conf Rm # 1135, Marina Del Rey

    WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=9e22bdf6c8be40a3a5f7abdb6c3fef251d

    Audiences: Everyone Is Invited

    Posted By: Peter Zamar

  • CS Colloquium: Ari Shapiro (ICT) - Models of Motion, Movement and Interaction for Digital Characters

    Fri, May 01, 2015 @ 01:00 PM - 02:20 PM

    Computer Science

    Conferences, Lectures, & Seminars

    Speaker: Ari Shapiro, USC Institute for Creative Technologies

    Talk Title: Models of Motion, Movement and Interaction for Digital Characters

    Series: CS Colloquium

    Abstract: Research in animation has progressed where capture technologies have allowed recording and playback of human motion. For example, a human face can be recorded speaking an utterance, then accurately modeled in 3D. However, making the 3D face produce an utterance that has not previously been recorded requires an understanding of how the face reacts to the speech that is generated, how the head and neck must move to accommodate that sound as well as that expression, and how the other parts of the face and eyes act during the speech. Similarly, motion capture techniques allow the capture and replication of human walking or running as performed by the original actor, but arbitrary movement through uneven terrain with obstacles cannot be synthesized accurately, since the complexity of the human balance and structure is not accurately modeled using only kinematic points in space over time.

    Thus, while motion replication into a 3D environment is fairly well understood across a number of areas, the fundamental question of how to synthesize movement through a controllable model of humans remains elusive. The human body is extremely complex, and models of movement for high energy activities such as running differ greatly from other complex phenomena such as talking or gesturing. Thus, while it is possible to replicate a recorded motion, generating a controllable model of movement for a virtual human remains an open research problem for many different areas, ranging from facial expression to speech to gross movement. In addition, the motivations for human movement and motion are often driven by cognitive functions, so a better understanding of human movement requires a similar understanding of the cognitive aspects that motivate it.

    In this talk, I will describe my research in generating various controllable models of motion and movement for animated 3D characters. My objective is to better understand how people physically move, interact and respond to people and objects in their environment By better understanding how people move about and the motivations for doing so, we can create models of human movement and behavior that can be controlled within a virtual or digital space, thus enabling convincing virtual characters that can be used for various types of training and simulation. The embodiment of movement and behavior of a person into a controllable, digital model allows for the creation of complicated scenarios that can be effective substitutes and training environments for real-world experiences.

    The lecture will be available to stream HERE. (Right Click, New Tab for optimal results.)

    Biography: Ari Shapiro currently works as a Research Scientist at the USC Institute for Creative Technologies, where his focus is on synthesizing realistic animation for virtual characters as lead of the Character Animation and Simulation research group. Shapiro has published many academic articles in the field of computer graphics and animation for virtual characters, and is a seven-time SIGGRAPH speaker.
    For several years, he worked on character animation tools and algorithms in the research and development departments of visual effects and video games companies such as Industrial Light and Magic, LucasArts and Rhythm and Hues Studios. He has worked on many feature-length films, and holds film credits in The Incredible Hulk and Alvin and the Chipmunks 2. In addition, he holds video games credits in the Star Wars: The Force Unleashed series.
    He completed his Ph.D. in computer science at UCLA in 2007 in the field of computer graphics with a dissertation on character animation using motion capture, physics and machine learning. He also holds an M.S. in computer science from UCLA, and a B.A. in computer science from the University of California, Santa Cruz.

    Host: CS Department

    Webcast: https://bluejeans.com/57723254

    Location: Grace Ford Salvatori Hall Of Letters, Arts & Sciences (GFS) - 108

    WebCast Link: https://bluejeans.com/577232541

    Audiences: Everyone Is Invited

    Posted By: Assistant to CS chair

  • Learning Longer Memory in Recurrent Networks

    Tue, May 12, 2015 @ 11:00 AM - 12:00 PM

    Information Sciences Institute

    Conferences, Lectures, & Seminars

    Speaker: Tomas Mikolov , Research Scientist at Facebook AI Reseach

    Talk Title: Learning Longer Memory in Recurrent Networks

    Series: AISeminar

    Abstract: Recurrent neural network is a powerful model that learns temporal patterns in sequential data. For a long time, it was believed that recurrent networks are difficult to train using simple optimizers, such as stochastic gradient descent, due to the so-called vanishing gradient problem. In this talk, I will show that learning longer term patterns in real data, such as in natural language, is perfectly possible using gradient descent. This is achieved by using a slight structural modification of the simple recurrent neural network architecture. Some of the hidden units are encouraged to change their state slowly by constraining part of the recurrent weight matrix to be close to identity, thus forming kind of a longer term memory. We evaluate our model in language modeling experiments, where we obtain similar performance to the much more complex Long Short Term Memory (LSTM) networks. This is a joint work with Armand Joulin, Sumit Chopra, Michael Mathieu and Marc'Aurelio Ranzato.

    Biography: Tomas Mikolov is a research scientist at Facebook AI Research. His work includes introduction of recurrent neural networks to statistical language modeling (published as open-source RNNLM toolkit), and an efficient algorithm for estimating word representations in continuous space (the Word2vec project). His current interest is in developing techniques and datasets that would help to advance research towards artificial intelligence systems capable of natural communication with people.

    Website: https://research.facebook.com/researchers/643234929129233/tomas-mikolov/

    Host: Ashish Vaswani

    Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=19140806ae5e4116ab2644b1c1d86bbe1

    Location: Information Science Institute (ISI) - 1135

    WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=19140806ae5e4116ab2644b1c1d86bbe1d

    Audiences: Everyone Is Invited

    Posted By: Alma Nava / Information Sciences Institute

  • AI Seminar: Computerized Search for Causal Relations in High Dimensional Data: Some Results and Many Problems

    Wed, May 13, 2015 @ 11:00 AM - 12:00 PM

    Information Sciences Institute

    Conferences, Lectures, & Seminars

    Speaker: Clark Glymour , Alumni University Professor, Carnegie Mellon University

    Talk Title: Computerized Search for Causal Relations in High Dimensional Data: Some Results and Many Problems

    Series: Artificial Intelligence Seminar

    Abstract: I will briefly review the graphical causal model framework and describe some of the search strategies that have proved practical in small dimensional problems. Then I will describe some of the modifications we have recently pursued at Carnegie Mellon to allow search in high dimensional problems, e.g, 50.000 - 1,000,000 variables, with sample sizes orders of magnitude smaller, and some of the many problems we have not satisfactorily solved.

    Biography: Clark Glymour is the Alumni University Professor in the Department of Philosophy at Carnegie Mellon University. He is also a senior research scientist at the Florida Institute for Human and Machine Cognition. He is the founder of the Philosophy Department at Carnegie Mellon University, a Guggenheim Fellow, a Fellow of the Center for Advanced Study in Behavioral Sciences a Phi Beta Kappa lecturer, and is a Fellow of the statistics section of the AAAS. Glymour and his collaborators created the causal interpretation of Bayes nets and developed an automated causal inference algorithm implemented as software named TETRAD. His areas of interest include epistemology (particularly Android epistemology), machine learning, automated reasoning, psychology of judgment, and mathematical psychology.

    Host: Kun Zhang

    More Info: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=ebaa5ed5e1444cbfa7aea272f321509d1d
    Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=ebaa5ed5e1444cbfa7aea272f321509d1

    Location: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey

    WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=ebaa5ed5e1444cbfa7aea272f321509d1d

    Audiences: Everyone Is Invited

    Posted By: Peter Zamar

  • Artificial vs AuthenticThe Art of Language Invention

    Tue, May 19, 2015 @ 03:00 PM - 04:00 PM

    Information Sciences Institute

    Conferences, Lectures, & Seminars

    Speaker: David Peterson , HBOs Game of Thrones

    Talk Title: Artificial vs Authentic:The Art of Language Invention

    Series: Artificial Intelligence Seminar

    Abstract: As long as humans have been using language, humans have been inventing language. Linguistic creativity has taken many different forms over the years, but it's made its greatest strides in the past 25 years. For languages like Esperanto and Volapük, functionality and unambiguity were lofty design goals. Today, with languages created for entirely different purposes, functionality is considered a prerequisite, and unambiguity a major design flaw. In this talk, David Peterson discusses naturalistic language creation, and the emerging art form known as conlanging.

    Biography: David Peterson is a language creator and author. Since 2009, he's been working on HBO's Game of Thrones, having created the Dothraki and Valyrian languages. Since then, he's gone on to work on a number of other projects, including Syfy's Defiance, Syfy's Dominion, Marvel's Thor: The Dark World, the CW's Star-Crossed, the CW's The 100, and Showtime's Penny Dreadful. He authored the book Living Language Dothraki, an introductory guide to the Dothraki language, and in September, he'll be publishing The Art of Language Invention with Penguin Random House.

    Host: Ashish Vaswani

    More Info: http://webcasterms1.isi.edu/mediasite/SilverlightPlayer/Default.aspx?peid=714b19be3e114ca79ddb3ccfb55366f01d
    Webcast: http://webcasterms1.isi.edu/mediasite/SilverlightPlayer/Default.aspx?peid=714b19be3e114ca79ddb3ccfb55366f01

    Location: Information Science Institute (ISI) - 11th Flr Conf Rm s1135 & 1137 Marina Del Rey

    WebCast Link: http://webcasterms1.isi.edu/mediasite/SilverlightPlayer/Default.aspx?peid=714b19be3e114ca79ddb3ccfb55366f01d

    Audiences: Everyone Is Invited

    Posted By: Peter Zamar