Fall 2018 Colloquium Speakers

Sean Devlin (TCNJ)
Deep Reinforcement Learning: The fundamentals of how AI wins games and beyond

12:30 – 1:30 PM
Tuesday, September 18, 2018
Location: SCP 101

Abstract: It was once believed that if a computer could beat a chess champion, then AI would be achieved. This belief was later changed from chess to go and now that go has been tackled, much more complicated games like Dota 2 are in the cross hairs with general artificial intelligence still in the distance. This talk will provide the fundamentals of deep reinforcement learning, the primary field of AI being used to accomplish these feats. We will start with an intro to reinforcement learning, dig into Google Deep Mind’s seminal 2013 paper “Playing Atari with Deep Reinforcement Learning”, and conclude with the directional vector of this very hyped field of research.

Speaker Bio: Sean Devlin: First and foremost a modern family man. Currently an Entrepreneur in Residence at TCNJ. Previously a technical co-founder at Front Rush.

Sharif Mohammad Shahnewaz Ferdous (TCNJ)
Virtual Reality and Serious Games

12:30 – 1:30 PM
Friday, November 2, 2018
Location: SCP 101

Abstract: Virtual Reality (VR) is a computer-generated simulation that uses visual, auditory and other sensory feedback to provide a user with an immersive experience. While visual feedback is the most important component of a VR experience, other sensory feedback plays important roles too. A well composed VR system has many usages including serious games. While a VR system can be used for entertainment purposes, in serious games, we focus on education, health care, emergency management, city planning, engineering, scientific exploration, politics etc. VR is being used in rehabilitation of stroke patients, balance impairments, post-traumatic stress disorder (PTSD), pain management, and so on. It is also being used for military training, surgical training, car modeling, etc. This talk will discuss the prospects and the presenter’s experience on of using VR in serious games. It will also provide some aspects of the presenter’s current work on assessing gender bias on self-reported cybersickness – a sickness induced by using VR systems for a long time.

Speaker Bio: Dr. Sharif Mohammad Shahnewaz Ferdous is an Assistant Professor at the Department of Computer Science of The College of New Jersey. He earned his Ph.D. in Computer Science from the University of Texas at San Antonio (UTSA). Prior to that, he completed his bachelor’s degree in Computer Science and Engineering from Bangladesh University of Engineering and Technology (BUET), Bangladesh. His research interests include Virtual Reality, Mixed Reality, Augmented Reality, Serious Games, 3D User Interfaces, Interactive Computer Graphics, and Human-Computer Interaction. His Ph.D. dissertation was focused on Improving accessibility of Virtual and Augmented Reality for people with balance impairments.

Davide Schaumann (Rutgers University)
Buildings, People, and Human Behavior

12:30 – 1:30 PM
Tuesday, November 20, 2018
Location: SCP 101

Abstract: The computational tools that architects use to design buildings provide a static representation of built environments, which does not consider the people who will inhabit the spaces, and their future activities. In this talk, we will explore our efforts to produce dynamic representations of buildings in use, prior to their construction and occupancy. Our goal is to help architects analyze human-building interactions during the design phase, when design issues can be discovered and addressed. In particular, we will discuss computational methods to model and simulate human behavior patterns in not-yet-built environments, their applications for designing complex buildings (like hospitals), and initial results from integrating them within established architectural design tools to conduct static and dynamic human behavior analyses and to optimize the building design with respect to human-related performance criteria. Additionally, we will discuss the potential application of human behavior simulation methods to explore how IT-enhanced environments may affect the behavior of building occupants at the building and city scale.

Speaker Bio: Davide Schaumann is a Postdoctoral fellow in the Department of Computer Science at Rutgers University. He received his PhD from the Faculty of Architecture and Town Planning at the Technion – Israel Institute of Technology, and he holds MSc and B.A. degrees in Architecture from the Politecnico di Milano, Italy. Davide’s research lies at the intersection of Architectural Design, Artificial Intelligence, and Human Behavior Science with a mission to apply digital technologies for analyzing the dynamic interactions between people, the spaces they inhabit, and the activities they engage in. Davide won several prices and was recently awarded the Murray Fellowship to support his Postdoctoral position.