6:30 pm: Welcomes and Thank You

6:35 pm:  Bart Gajderowicz

Title: Artificial Intelligence Planning Techniques for Emulating Agentswith Application in Social Services

Bart is a fourth year PhD candidate in the Mechanical and Industrial Engineering Dept. at the University of Toronto, under the supervision of Professors Mark S. Fox and Michael Grüninger. He is a member of the Centre for Social Services Engineering working on the Social Service Simulator project. He holds a MSc and BSc degrees in Computer Science from Ryerson University where he co-founded the Ubiquitous and Pervasive Computing Laboratory. Bart’s current work applies artificial intelligence technique to understanding human behaviour, with a focus on evaluating social service policies. Prior to joining the CSSE, Bart spent 12 years as a Software Engineer.

Summary: 

In this presentation I will identify challenges in predicting social behaviour with a focus on social service clients.  I will present quantitative methods for tackling the next generation of problems for increasingly connected and disconnected societies. I will introduce the work being done at the Centre for Social Services Engineering and our partners that span different disciplines and organizations.  I will then discuss my research that focuses on evaluating social service policies using computer simulation and predicting behaviour of homeless clients.

Abstract:

Tools for evaluating social service policy lack a sufficient representation of the client and their behaviour in response to different policies. Methods for predicting human behaviour have been successful for applications like ranking search results, anticipating customer behaviour, newsfeed aggregation, and transportation systems. The surge in available data and improvements in algorithm efficiency has increased the quality of such recommendation systems. Traditional data sources have included crowd-sourcing, search keywords, buying behaviour, and new-media (social media, wikis, blogs, online news, etc).

Challenges exist in applying such systems to emerging and underrepresented societies, such as the homeless population. A key limitation lies in recommendation systems that learn from like-minded communities within an echo-chamber of ideas, converging on the social norms of those communities. As a result, many underrepresented communities exist in our society to whom such systems do not apply.

Where data is lacking, theories of behaviour from social sciences have been filling the gap with key contributions from areas like behaviour psychology, neural science, cognitive science, and behaviour economics.  A growing challenge for the machine intelligence community is to develop new methods that can successfully incorporate such theories and look beyond the echo chambers to address the needs of emerging societies.

7:55 pm: Thank Yous

Thank you to Georgian Partners for the extra space!

Both audiences, those who are interested in machine intelligence / data science, and those who are practitioners of machine intelligence / data science are invited, and can both expect to learn something new.

Attendees can expect to learn what machine intelligence is, its applications, and what’s going on in Toronto’s data science community. Significant getting to know you time, and Q&A time is deliberately set aside.

Back to all