Simon Fraser University
Engaging the World

Gabor Melli, Senior Director of Engineering at Sony PlayStation

Talk Title: Global-Scale Contextual Low-Latency Near Real-Time Data-Driven Personalization

Abstract: Predictive machine learning is powering innovation across industries, including healthcare, finance, media & entertainment, and many more.

This brief talk describes the successful development process at Sony Interactive Entertainment for the delivery of scalable real-time low-latency predictive ML-based solutions on the cloud, such as for the PS5 PlayStation console.

Bio: Gabor Melli is Senior Director of Engineering (ML&AI) at Sony PlayStation. He received his PhD in Computing Science at Simon Fraser University. He has twenty-plus years of experience in delivering large-scale data-driven mission critical solutions at both enterprises ranging from Sony PlayStation, AT&T, Microsoft, T-Mobile and Wal*Mart, and several start-ups. He continues to publish, present and organize world-class conferences.

Saba Alimadadi, Assistant Professor, School of Computing Science 

Talk Title: Understanding Motifs of Program Behaviour

Abstract: “Software is eating the world.” Today’s complex and large programs are not easy to comprehend, and are thus not immune to bugs. Program comprehension is crucial in software engineering; a necessary step for performing many tasks. However, the implicit and intricate relations between program entities hinder comprehension of program behaviour and can easily lead to bugs, which can have severe consequences.

At the conjunction of software engineering, programming languages, and human-computer interaction, my research aims at improving the performance of developers. Using semi-automated static and dynamic techniques, I create behavioural models of program execution and visualize them for developers in order to facilitate the process of program comprehension and debugging. The outcome of my work is a set of open-source tools, which I evaluate through controlled experiments in realistic settings. The results show that my methods significantly improve developers’ performance in their everyday tasks.

Bio: Saba Alimadadi is an assistant professor in the School of Computing Science at Simon Fraser University (SFU). Previously, she was an NSERC PDF postdoctoral researcher at Northeastern University. She received her PhD from the University of British Columbia (UBC) in 2017. Saba’s research is in the area of software engineering, with a focus on program analysis, comprehension, and debugging. She is the recipient of an ACM SIGSOFT Distinguished Paper Award at ICSE and ranked first in the CS division of the NSERC PDF competition in 2018.

Angel Xuan Chang, Assistant Professor, School of Computing Science 

Talk title: Grounding natural language to 3D

Abstract: In popular imagination, household robots that we can instruct to "bring me my red mug from the kitchen" or ask “where are my glasses?” are common.  For a robot to execute such an instruction or answer such a question, it needs to parse and interpret natural language, understand the 3D environment it is in (e.g. what objects exist and how they are described), navigate to locate the target object, and then formulate an appropriate response.  While there has been previous work on the language-to-vision grounding problem in the 2D domain, there is much less work on methods operating with 3D representations such as required by the scenarios in these examples.  In this talk, I will provide an overview of recent work in my group to connect language to 3D representations.

Bio: Angel Xuan Chang is an Assistant Professor of Computer Science at Simon Fraser University. Dr. Chang’s research focuses on the intersection of natural language understanding, computer graphics, and AI. Her research connects language to 3D representations of shapes and scenes and addresses grounding of language for embodied agents in indoor environments. She has worked on methods for synthesizing 3D scenes and shapes, 3D scene understanding, and helped to create various datasets for 3D deep learning (ShapeNet, ScanNet, Matterport3D). She received her Ph.D. in Computer Science from Stanford, under the supervision of Chris Manning. Dr. Chang received the SGP 2018 Dataset Award for her work on the ShapeNet dataset. She is a recipient of the TUM-IAS Hans Fischer Fellowship and a Canada CIFAR AI Chair.

Ke Li, Assistant Professor, School of Computing Science

Talk Title: Worry-Free Image Synthesis without Mode Collapse

Abstract: Generative adversarial nets (GANs) are the workhorse of deep learning-based image synthesis methods. In practice, however, they suffer from the well-documented problem of mode collapse and effectively ignore arbitrary subsets of the training data. This problem has proven to be difficult to solve and has persisted through the many successive variants of GANs. I will illustrate why mode collapse happens fundamentally and show how to overcome it, which forms the basis of a new method known as Implicit Maximum Likelihood Estimation (IMLE). In the conditional setting, IMLE overcomes the tendency of GANs to ignore the latent noise and can generate alternative versions of images that are unobserved. 

Bio: Ke Li is an Assistant Professor in the School of Computing Science at Simon Fraser University. He is interested in a broad range of topics in machine learning, computer vision, NLP and algorithms and has worked on generative modelling, nearest neighbour search and Learning to Optimize. He is particularly passionate about tackling long-standing fundamental problems that cannot be tackled with a straightforward application of conventional techniques. He was previously a Member of the Institute for Advanced Study (IAS), and received his Ph.D. from UC Berkeley and B.Sc. from the University of Toronto.