Free

Towards General and Robust AI at Scale

Actions and Detail Panel

Free

Event Information

Share this event

Date and time

Location

Location

Online event

Event description
IARAI - Institute of Advanced Research in Artificial Intelligence | Towards General and Robust AI at Scale

About this event

Towards General and Robust AI at Scale - Dr Irina Rish

Link to register: https://www.iarai.ac.at/events/towards-general-and-robust-ai-at-scale/

______________________________________________

Modern AI systems have achieved impressive results in many specific domains, from image and speech recognition to natural language processing and mastering complex games such as chess and Go. However, they often remain inflexible, fragile and narrow, unable to continually adapt to a wide range of changing environments and novel tasks without “catastrophically forgetting” what they have learned before, to infer higher-order abstractions allowing for systematic generalization to out-of-distribution data, and to achieve the level of robustness necessary to “survive” various perturbations in their environment – a natural property of most biological intelligent systems, and a necessary property for successfully deploying AI systems in real-life applications.

In this talk, Dr Rish will provide a brief overview of their recent efforts towards making AI more broad (i.e., general/versatile) and more robust, focusing on continual learning, invariance and adversarial robustness. Our speaker will emphasize the importance of developing an empirical science of AI behaviors, and focus on the rapidly expanding field of neural scaling laws, which allows to better compare and extrapolate behavior of various algorithms and models with increasing amounts of data, model size and computational resources. Finally, Dr Rish will summarize their recent work on applying machine learning models to neuroscience and brain imaging.

Irina Rish is an Associate Professor in the Computer Science and Operations Research Department at the Université de Montréal (UdeM) and a core faculty member of Mila - Quebec Artificial Intelligence Institute. She holds Canada Excellence Research Chairs (CERC) in Autonomous AI and a Canadian Institute for Advanced Research (CIFAR) Canada AI Chair. She received her MSc and PhD in AI from UC Irvine and MSc in Applied Mathematics from Gubkin Russian State University of Oil and Gas (National Research University). Dr Rish’s research focus is on machine learning, neural data analysis and neuroscience-inspired AI. Before joining UdeM and MILA in 2019, Irina was a research scientist at the IBM T.J. Watson Research Center, where she worked on various projects at the intersection of neuroscience and AI, and led the Neuro-AI challenge.

This session will be held on Zoom and live streamed on YouTube.


		Towards General and Robust AI at Scale image
Share with friends

Date and time

Location

Online event

{ _('Organizer Image')}

Organizer IARAI

Organizer of Towards General and Robust AI at Scale

The Institute advances basic and applied research in Artificial Intelligence

We are building a unique environment of world class researchers and industrial-scale real-world data openly shared with the scientific community. We take a proudly interdisciplinary approach to bring together top talent from complementary fields, combining in-depth domain knowledge in AI, simulation, and geospatial analysis from academia and industry. All our research is open and published.

Contact us to contribute and join us.

We organize and sponsor scientific visits, research exchanges, multi-month thematic focus programmes, and academic competitions such as Traffic4cast at NeurIPS

IARAI - Institute of Advanced Research in Artificial Intelligence

www.iarai.org LinkedIn Twitter

Save This Event

Event Saved