AI Innovation Institute

George Em Karniadakis received his SM and PhD from Massachusetts Institute of Technology. He was appointed lecturer in the Department of Mechanical Engineering at MIT in 1987 and subsequently he joined the Center for Turbulence Research at Stanford/Nasa Ames. He joined Princeton University as assistant professor in the Department of Mechanical and Aerospace Engineering and as associate faculty in the program of applied and computational mathematics. He was a visiting professor at Caltech in 1993 in the Aeronautics Department and joined Brown University as associate professor of applied mathematics in the Center for Fluid Mechanics in 1994. After becoming a full professor in 1996, he continues to be a visiting professor and senior lecturer of Ocean/Mechanical Engineering at MIT. He is an AAAS fellow (2018), fellow of the Society for Industrial and Applied Mathematics (2010), fellow of the American Physical Society (2004), fellow of the American Society of Mechanical Engineers (2003) and associate fellow of the American Institute of Aeronautics and Astronautics (2006). He received the Alexander von Humboldt award in 2017, the Ralf E Kleinman award (2015), the J. Tinsley Oden Medal (2013), and the CFD award (2007) from the US Association in Computational Mechanics. His h-index is 103, and he has been cited over 52,000 times.


Abstract:
Karniadakis will present a new approach to develop a data-driven, learning-based framework for predicting outcomes of physical and biological systems, governed by PDEs, and for discovering hidden physics from noisy data. He will introduce a deep learning approach based on neural networks (NNs) and generative adversarial networks (GANs). He will also introduce new NNs that learn functionals and nonlinear operators from functions and corresponding responses for system identification. Unlike other approaches that rely on big data, here we learn from small data by exploiting the information provided by the physical conservation laws, which are used to obtain informative priors or regularize the neural networks. He will demonstrate the power of PINNs for several inverse problems in fluid mechanics, solid mechanics and biomedicine including wake flows, shock tube problems, material characterization, brain aneurysms, etc., where traditional methods fail due to lack of boundary and initial conditions or material properties. He will also present a new NN, DeepM&Mnet, which uses DeepOnets as building blocks for multiphysics problems, and he will demonstrate its unique capability in a 7-field hypersonics application.  

To register and for more information, click here.  

The Natural Language Processing Reading Group at Stony Brook University meets weekly to discuss recent research papers in NLP and related fields. Join the Google Group here.

Don't Just Fix it in Post: A Science of AI Must Study Training Dynamics


Abstract: What would it mean to have a scientific understanding of AI? Models are not static objects: they are snapshots of time-evolving processes shaped by data, objectives, architectures, and optimization dynamics. Yet much of AI research treats models as fixed artifacts, analyzing behaviors after training rather than asking why they emerge. This position paper argues that a science of AI must move beyond post hoc fixes and study the training dynamics that produce model behavior. Such a science should support progressively stronger forms of understanding: predicting outcomes from early training signals, intervening when trajectories go wrong, and ultimately designing training procedures that more reliably produce desired properties. Scaling laws have made prediction routine for loss; the challenge is extending this success to capabilities, biases, robustness, and safety-relevant behaviors. We articulate requirements for such theories grounded in the history and philosophy of science, examine progress in mechanistic interpretability, fairness, memorization, and simplicity bias, and identify concrete open problems.
Location: NCS 220

Zoom Link: https://stonybrook.zoom.us/j/92942833294?pwd=ysKMaQx7Hp0lkq5nOb3zJ9ivNZVvLv.1

How to Succeed in Language Design Without Really Trying presented by Professor Brian Kernighan

ABSTRACT: Why do some languages succeed while others fall by the wayside? I've helped create nearly a dozen languages (mostly small) over the years; a handful are still in widespread use, while others have languished or simply disappeared. I've also been present at the creation of several other languages, including some really major ones. In this talk I'll give my humble, but correct, opinion on factors that affect success and failure, and try to offer some insight into what to do if you're trying to design a new language yourself, and why that might be a good thing.

BIO: Brian Kernighan received a PhD in electrical engineering from Princeton in 1969. He joined the Computer Science department at Princeton in 2000, after many years at Bell Labs. He is a co-creator of several programming languages, including AWK and AMPL, and of a number of tools for document preparation. He is the co-author of a dozen books and some technical papers, and holds 5 patents.
He is a member of the National Academy of Engineering and of the American Academy of Arts and Sciences. His research areas include programming languages, tools and interfaces that make computers easier to use, often for non-specialist users. He has also written two books on technology for
non-technical audiences: Understanding the Digital World in 2017 and Millions, Billions, Zillions: Defending Yourself in a World of Too Many Numbers, published in 2018. His most recent book, Unix: A History and a Memoir, was published in October 2019.

talk at 4:00 in 214

Communication-Efficient Heterogeneity-Aware Machine Learning System and Architecture by Xuehai Qian

ABSTRACT: The key success of deep learning is the increasing size of models that can achieve high accuracy. At the same time, it is difficult to train the complex models with large data sets. Therefore, it is crucial to accelerate training with distributed systems and architectures, where communication and heterogeneity are two key challenges. In this talk, I will present two heterogeneity-aware decentralized training protocols without communication bottleneck. Specifically, Hop supports arbitrary iteration gap between workers by novel queue-based synchronization which can tolerate heterogeneity with system techniques. Prague uses randomized communication to tolerate heterogeneity with a new training algorithm based on partial reduce -- an efficient communication primitive. If time permits, I will present the systematic tensor partitioning for training on heterogeneous accelerator arrays (e.g., GPU/TPU). We believe that our principled approaches are crucial for achieving high-performance and efficient distributed training.

BIO: Xuehai Qian is an assistant professor at University of Southern California. His research interests include domain-specific systems and architectures, performance tuning and resource management of cloud systems and parallel computer architectures. He received his PhD from the University of Illinois Urbana Champaign and was a postdoc at UC Berkeley. He is the recipient of W.J Poppelbaum Memorial Award at UIUC, NSF CRII and CAREER Award, and the inaugural ACSIC (American Chinese Scholar In Computing) Rising Star Award.

Virtual Talk: Metadata Matters: Robust Document Classification via Adaptation Methods for Text-driven Public Health by Xiaolei Huang

Zoom link to follow.

Abstract: Document classifiers have been widely applied in solving health-related issues, such as suicide prevention, flu vaccination surveillance and disease diagnosis. However, document metadata including time, gender, age and location has an enormous impact on robustness of 
document classifiers. Language varies across the metadata bringing both challenges and opportunities to build reliable document classifiers. For example, online written language changes over time, and males and females express opinions differently. This talk describes how to use domain adaptation to integrate temporal and user demographic factors into document classifiers. By adapting knowledge of how language varies across the metadata, models can learn generalized representations of language through the metadata-invariant embeddings. 
This approach will lead to metadata-adapted document classifiers and can also extend to personalize classification models by user embedding. 

Bio: Xiaolei Huang is a 4th-year PhD candidate in Information Science at the University of Colorado, Boulder. He is currently a visiting scholar at the Johns Hopkins University. His research interests are in Natural Language Processing, Machine Learning and Public Health. Particularly, he focuses on domain adaptation, cross-lingual transfer learning, user modeling and fairness.

IACS Research Theme: Human Centered Computing Seminar

Abstract: The AI art platform Artbreeder hosts daily remix parties where users build on each other's work, creating transparent evolutionary chains of images from a single seed. This study analyzes 130,882 images from 368 remix parties to identify the drivers of novelty, complexity, and competitive success. The results reveal an interesting tension: while more novel parent images produce more novel and complex children and attract more likes, users paradoxically prefer to remix images that are less novel and complex. At the group level, larger remix parties produce more novelty at the cost of lower complexity. Additionally, images tend to converge towards common thematic attractors (e.g., steampunk scenes, alien architecture, furries) over the course of remix parties. These results provide quantitative insights into collective creativity--the production of novelty by groups of people--a typically opaque aspect of human cultural evolution.

Speaker: Dr. Mason Youngblood

Location: Institute for Advanced Computational Science, Seminar Room