Clark Atlanta University (CAU), in collaboration with Georgia Tech’s NSF Artificial Intelligence (AI) Research Institute for Advances in Optimization (AI4OPT), has been awarded a four-year $2.79 million grant (Award ID 2402493) by the National Science Foundation (NSF) to create an AI Hub. This collaborative effort aims to advance AI education and research at minority-serving institutions, particularly historically Black colleges and universities (HBCUs).

This initiative, part of the NSF ExpandAI program, aims to boost minority-serving institution participation in AI research, education, and workforce development through capacity-building projects and partnerships within the NSF-led National AI Research Institutes ecosystem.

Building an AI community is no easy feat, but the CAU-GT/AI4OPT collaboration is prepared to meet it. The project, known as AIHUB@CAU, will be led by principal investigator Charles B. Pierre, associate professor in CAU’s Department of Mathematical Sciences.

"The mission of the grant aligns with the AI4OPT Faculty Training Program, which focuses on strategies to increase minority participation in AI research programs from HBCUs to other minority-serving institutions," said Pierre, who also leads the Educational and Diversity Initiatives at AI4OPT. "Our goal is to ensure diverse representation in the AI field."

The collaboration will use existing educational resources and infrastructure to build centers of excellence in AI and a community of empowered Black AI researchers. 

"We anticipate challenges in developing coursework, including finding qualified industry professionals to teach and preparing academic professors unfamiliar with AI," Pierre said. "Our aim is to establish Ph.D. programs at CAU and position the university as a hub for AI training, addressing these issues head-on."

AIHUB@CAU will integrate industry partnerships to accelerate curriculum development and real-world applications. It expands AI education beyond machine learning to encompass decision-making and applications in fields like business analytics, cyber-physical security, and operations research.

Partially funded through NSF's Louis Stokes Alliances for Minority Participation program, this award underscores NSF's commitment to diversity in STEM fields through impactful educational and research initiatives.

"Establishing programs at institutions like Clark Atlanta University and AI4OPT at Georgia Tech provides students with essential resources and tools to succeed in this ever-evolving field," Pierre noted.

Goals and Structure of the AI Education Program

Main Goals of Creating AI Courses at the Undergraduate and Graduate Levels:

• Close the gap of AI graduates from HBCUs at undergraduate and graduate levels.
• Prepare HBCU students for the AI workforce.
• Align with the vision of AI4OPT at Georgia Tech to "democratize access to AI education."

Impact on Students' Career Prospects and the AI Research Community:

• Undergraduate courses and programs will prepare students for entry-level positions in the field.
• Graduate courses and programs will prepare students for research and participation in the AI research community.

Role and Contribution:

• AI4OPT at Georgia Tech will assist CAU with the development of both undergraduate and graduate courses and programs.
• Offer research opportunities to CAU students at the undergraduate and graduate levels.
• AI4OPT at Georgia Tech will be a partner in the established AI Research Hub.

Support for Development of MS and Ph.D. Courses:

• Use current courses at Georgia Tech as a template.
• Use the courses offered through the Faculty Training Program (FTP) of AI4OPT.

Foundational AI Courses:

• Courses already taught by CAU faculty in the AI4OPT FTP.
• Courses available at Georgia Tech.
• New courses to be developed by AIHUB@CAU based on Intel material, focusing on computer vision and natural language processing.
• Courses in applied optimization developed by AI4OPT.
• New use-inspired AI courses teaching applications of AI in various domains, such as supply chains, security, chemistry, and manufacturing.

Research Opportunities:

• The Undergraduate Research Program (URP) will provide students with early exposure to AI research, including summer internships at Georgia Tech and other AI4OPT sites.
• The graduate programs will include an 18-month non-thesis master's degree with a summer internship and capstone project, and a two-year thesis master's degree supported by a six-month research project.

Structure of the New Master in AI Program:

• Courses in five categories to support the master’s program:
  1. Existing courses at CAU taught in the AI4OPT FTP.
  2. Courses available at Georgia Tech.
  3. New courses based on Intel material.
  4. Applied optimization courses developed by AI4OPT.
  5. New courses developed by AIHUB@CAU focusing on AI applications in various domains.

Collaborations and Internships:

• Joint supervision of research projects by CAU and AI4OPT faculty.
• Summer internships starting in 2026.
• Capstone projects facilitated by Georgia Tech and industrial partners.

About AI4OPT

The Artificial Intelligence (AI) Research Institute for Advances in Optimization, or AI4OPT, aims to deliver a paradigm shift in automated decision-making at massive scales by fusing AI and Mathematical Optimization (MO) to achieve breakthroughs that neither field can achieve independently. The Institute is driven by societal challenges in energy, logistics and supply chains, resilience and sustainability, and circuit design and control. To address the widening gap in job opportunities, the Institute delivers an innovative longitudinal education and workforce development program.

About Georgia Tech

The Georgia Institute of Technology, or Georgia Tech, is a top 10 public research university developing leaders who advance technology and improve the human condition. The Institute offers business, computing, design, engineering, liberal arts, and sciences degrees. Its nearly 40,000 students, representing 50 states and 149 countries, study at the main campus in Atlanta, at international campuses, and through distance and online learning. As a leading technological university, Georgia Tech is an engine of economic development for Georgia, the Southeast, and the nation, conducting more than $1 billion in research annually for government, industry, and society.

About Clark Atlanta University

Clark Atlanta University was formed with the consolidation of Atlanta University and Clark College, both of which hold unique places in the annals of African American history. Atlanta University, established in 1865 by the American Missionary Association, was the nation’s first institution to award graduate degrees to African Americans. CAU is also the largest of the 37-member UNCF institutions. CAU, established four years later in 1869, was the nation’s first four-year liberal arts college to serve a primarily African American student population. Today, with over 4,000 students, CAU is the largest of the four institutions (CAU, Morehouse College, Spelman College, and Morehouse School of Medicine) that comprise the Atlanta University Center Consortium.

About National Science Foundation

The U.S. National Science Foundation propels the nation forward by advancing fundamental research in all fields of science and engineering. NSF supports research and people by providing facilities, instruments and funding to support their ingenuity and sustain the U.S. as a global leader in research and innovation. With a fiscal year 2023 budget of $9.5 billion, NSF funds reach all 50 states through grants to nearly 2,000 colleges, universities and institutions. Each year, NSF receives more than 40,000 competitive proposals and makes about 11,000 new awards. Those awards include support for cooperative research with industry, Arctic and Antarctic research and operations, and U.S. participation in international scientific efforts.

When Blair Brettmann was a sophomore at the University of Texas at Austin, her advisor told her about the National Science Foundation’s Research Experience for Undergraduates (REU) program. The summer program enables undergraduates to conduct research at top institutions across the country. Brettmann spent the summer of 2005 at Cornell working in a national nanotechnology program — a defining experience that led to her current research in molecular engineering for integrated product development. 

“I didn't know for sure if I wanted to attend grad school until after the REU experience,” Brettmann said. “Through it, I went to high-level seminars for the first time, and working in a cleanroom was super cool.” 

Her experience was so positive that the following summer, Brettmann completed a second REU at the Massachusetts Institute of Technology, where she eventually earned her Ph.D. Now an associate professor in Georgia Tech’s School of Chemical and Biomolecular Engineering and School of Materials Science and Engineering and an Institute for Matter and Systems faculty member, Brettmann is an REU mentor for the current iteration of the nanotechnology program — now taking place at Georgia Tech. 

Brettmann’s mentee this summer, Marissa Moore, is having a similarly positive experience. A rising senior in chemical engineering at the University of Missouri-Columbia (Mizzou), Moore was already familiar with Georgia Tech because her father received his chemical engineering Ph.D. from the Institute; she hopes to do the same. Her passion for research began as she grew up with her sister, who had cerebral palsy and epilepsy. 

“We spent a lot of time in hospitals trying out new devices and looking for different medications that would help her, so I knew I wanted to make a difference in this area,” she said. 

But Moore wasn’t interested in being a doctor. Instead, she wanted to develop the materials that could be a solution for someone like her sister. Her undergraduate research focuses on materials and biomaterials for medical applications, and Georgia Tech is enabling her to deep-dive into pure materials science. 

“What I'm working on at both universities is biodegradable polymers, but at Mizzou I’m developing that polymer from the ground up, and at Tech I’m using the properties of the polymer and finding how to make them,” she explained. 

Having the opportunity to work in nanotechnology through the Institute for Materials and use Georgia Tech’s famous cleanroom made this REU stand out for Moore. 

“I had never been in the cleanroom before, so that was one of the most eye-opening experiences,” she said. “It was cool to gown up and learn all of the safety precautions.” 

For Brettmann, hands-on research experiences like this make the REU program unique — and crucial — for potential graduate students. 

“Having your experiments fail, or even having things not turn out as you expect them to is an important part of the graduate research experience,” she said. “One of the best things about REU is it can be a first experience for people and help them decide what to do in grad school later on.”

Georgia Tech will lead a consortium of 12 universities and 12 national labs as part of a $25 million U.S. Department of Energy National Nuclear Security Administration (NNSA) award. This is the second time Georgia Tech has won this award and led research and development efforts to aid NNSA’s nonproliferation, nuclear science, and security endeavors.

The Consortium for Enabling Technologies and Innovation (ETI) 2.0 will leverage the strong foundation of interdisciplinary, collaboration-driven technological innovation developed in the ETI Consortium funded in 2019. The technical mission of the ETI 2.0 team is to advance technologies across three core disciplines: data science and digital technologies in nuclear security and nonproliferation, precision environmental analysis for enhanced nuclear nonproliferation vigilance and emergency response, and emerging technologies. They will be advanced by research projects in novel radiation detectors, algorithms, testbeds, and digital twins.

“What we're trying to do is bring those emergent technologies that are not implemented right now to fruition,” said Anna Erickson, Woodruff Professor and associate chair for research in the George W. Woodruff School of Mechanical Engineering, who leads both grants. “We want to understand what's ahead in the future for both the technology and the threats, which will help us determine how we can address it today.” 

While half the original collaborators remain, Erickson sought new institutional partners for their research expertise, including Abilene Christian University, University of Alaska Fairbanks, Stony Brook University, Rensselaer Polytechnic Institute, and Virginia Commonwealth University. Other university collaborators include the Colorado School of Mines, the Massachusetts Institute of Technology, Ohio State University, Texas A&M University, the University of Texas at Austin, and the University of Wisconsin–Madison.  

National lab partners are the Argonne National Laboratory, Brookhaven National Laboratory, Idaho National Laboratory, Lawrence Berkeley National Laboratory, Lawrence Livermore National Laboratory, Los Alamos National Laboratory, Nevada National Security Site, Oak Ridge National Laboratory, Pacific Northwest National Laboratory, Princeton Plasma Physics Laboratory, Sandia National Laboratories, and Savannah River National Laboratory.

The partners, along with the other NNSA Consortia, gathered at Texas A&M in June to present the new results of the research — NNSA DNN R&D University Program Review — and the kickoff will be hosted in Atlanta in February 2025. More than 300 collaborators, including 150 students, met for four days to share their research and develop new partnerships. 

Engaging students in research in the nuclear nonproliferation field is a key part of the award. The plan is to train over 50 graduate students, provide internships for graduate and undergraduate students, and offer faculty-student lab visit fellowships. This pipeline aims to develop well-rounded professionals equipped with the expertise to tackle future nonproliferation challenges.

“Because nuclear proliferation is a multifaceted problem, we try to bring together people from outside nuclear engineering to have a conversation about the problems and solutions,” Erickson said.

“One of the biggest accomplishments of ETI 1.0 is this incredible relationship that our university PIs have been able to forge with national labs,” she said. “Over five years, we've supported over 70 student internships at national labs, and we have already transitioned a number of Ph.D. students to careers at national labs.” 

As the consortium efforts continue, the team looks forward to the next phase of engagement with government, university, and national lab partners.

“With a united team and a focus on cutting-edge technologies, the ETI 2.0 consortium is poised to break new ground in nuclear nonproliferation,” Erickson said. “Collaboration is the fuel, and innovation is the engine.”

Hepatic, or liver, disease affects more than 100 million people in the U.S. About 4.5 million adults (1.8%) have been diagnosed with liver disease, but it is estimated that between 80 and 100 million adults in the U.S. have undiagnosed fatty liver disease in varying stages. Over time, undiagnosed and untreated hepatic diseases can lead to cirrhosis, a severe scarring of the liver that cannot be reversed. 

Most hepatic diseases are chronic conditions that will be present over the life of the patient, but early detection improves overall health and the ability to manage specific conditions over time. Additionally, assessing patients over time allows for effective treatments to be adjusted as necessary. The standard protocol for diagnosis, as well as follow-up tissue assessment, is a biopsy after the return of an abnormal blood test, but biopsies are time-consuming and pose risks for the patient. Several non-invasive imaging techniques have been developed to assess the stiffness of liver tissue, an indication of scarring, including magnetic resonance elastography (MRE).

MRE combines elements of ultrasound and MRI imaging to create a visual map showing gradients of stiffness throughout the liver and is increasingly used to diagnose hepatic issues. MRE exams, however, can fail for many reasons, including patient motion, patient physiology, imaging issues, and mechanical issues such as improper wave generation or propagation in the liver. Determining the success of MRE exams depends on visual inspection of technologists and radiologists. With increasing work demands and workforce shortages, providing an accurate, automated way to classify image quality will create a streamlined approach and reduce the need for repeat scans. 

Professor Jun Ueda in the George W. Woodruff School of Mechanical Engineering and robotics Ph.D. student Heriberto Nieves, working with a team from the Icahn School of Medicine at Mount Sinai, have successfully applied deep learning techniques for accurate, automated quality control image assessment. The research, “Deep Learning-Enabled Automated Quality Control for Liver MR Elastography: Initial Results,” was published in the Journal of Magnetic Resonance Imaging.

Using five deep learning training models, an accuracy of 92% was achieved by the best-performing ensemble on retrospective MRE images of patients with varied liver stiffnesses. The team also achieved a return of the analyzed data within seconds. The rapidity of image quality return allows the technician to focus on adjusting hardware or patient orientation for re-scan in a single session, rather than requiring patients to return for costly and timely re-scans due to low-quality initial images.

This new research is a step toward streamlining the review pipeline for MRE using deep learning techniques, which have remained unexplored compared to other medical imaging modalities.  The research also provides a helpful baseline for future avenues of inquiry, such as assessing the health of the spleen or kidneys. It may also be applied to automation for image quality control for monitoring non-hepatic conditions, such as breast cancer or muscular dystrophy, in which tissue stiffness is an indicator of initial health and disease progression. Ueda, Nieves, and their team hope to test these models on Siemens Healthineers magnetic resonance scanners within the next year.

Publication
Nieves-Vazquez, H.A., Ozkaya, E., Meinhold, W., Geahchan, A., Bane, O., Ueda, J. and Taouli, B. (2024), Deep Learning-Enabled Automated Quality Control for Liver MR Elastography: Initial Results. J Magn Reson Imaging. https://doi.org/10.1002/jmri.29490

Prior Work 
Robotically Precise Diagnostics and Therapeutics for Degenerative Disc Disorder

Related Material
Editorial for “Deep Learning-Enabled Automated Quality Control for Liver MR Elastography: Initial Results”

New research from Georgia Tech is giving scientists more control options over generative artificial intelligence (AI) models in their studies. Greater customization from this research can lead to discovery of new drugs, materials, and other applications tailor-made for consumers.

The Tech group dubbed its method PRODIGY (PROjected DIffusion for controlled Graph Generation). PRODIGY enables diffusion models to generate 3D images of complex structures, such as molecules from chemical formulas. 

Scientists in pharmacology, materials science, social network analysis, and other fields can use PRODIGY to simulate large-scale networks. By generating 3D molecules from multiple graph datasets, the group proved that PRODIGY could handle complex structures.

In keeping with its name, PRODIGY is the first plug-and-play machine learning (ML) approach to controllable graph generation in diffusion models. This method overcomes a known limitation inhibiting diffusion models from broad use in science and engineering.

“We hope PRODIGY enables drug designers and scientists to generate structures that meet their precise needs,” said Kartik Sharma, lead researcher on the project. “It should also inspire future innovations to precisely control modern generative models across domains.” 

PRODIGY works on diffusion models, a generative AI model for computer vision tasks. While suitable for image creation and denoising, diffusion methods are limited because they cannot accurately generate graph representations of custom parameters a user provides.

PRODIGY empowers any pre-trained diffusion model for graph generation to produce graphs that meet specific, user-given constraints. This capability means, as an example, that a drug designer could use any diffusion model to design a molecule with a specific number of atoms and bonds.

The group tested PRODIGY on two molecular and five generic datasets to generate custom 2D and 3D structures. This approach ensured the method could create such complex structures, accounting for the atoms, bonds, structures, and other properties at play in molecules. 

Molecular generation experiments with PRODIGY directly impact chemistry, biology, pharmacology, materials science, and other fields. The researchers say PRODIGY has potential in other fields using large networks and datasets, such as social sciences and telecommunications.

These features led to PRODIGY’s acceptance for presentation at the upcoming International Conference on Machine Learning (ICML 2024). ICML 2024 is the leading international academic conference on ML. The conference is taking place July 21-27 in Vienna.

Assistant Professor Srijan Kumar is Sharma’s advisor and paper co-author. They worked with Tech alumnus Rakshit Trivedi (Ph.D. CS 2020), a Massachusetts Institute of Technology postdoctoral associate.

Twenty-four Georgia Tech faculty from the Colleges of Computing and Engineering will present 40 papers at ICML 2024. Kumar is one of six faculty representing the School of Computational Science and Engineering (CSE) at the conference.

Sharma is a fourth-year Ph.D. student studying computer science. He researches ML models for structured data that are reliable and easily controlled by users. While preparing for ICML, Sharma has been interning this summer at Microsoft Research in the Research for Industry lab.

“ICML is the pioneering conference for machine learning,” said Kumar. “A strong presence at ICML from Georgia Tech illustrates the ground-breaking research conducted by our students and faculty, including those in my research group.”

Visit https://sites.gatech.edu/research/icml-2024 for news and coverage of Georgia Tech research presented at ICML 2024.

A new machine learning (ML) model created at Georgia Tech is helping neuroscientists better understand communications between brain regions. Insights from the model could lead to personalized medicine, better brain-computer interfaces, and advances in neurotechnology.

The Georgia Tech group combined two current ML methods into their hybrid model called MRM-GP (Multi-Region Markovian Gaussian Process). 

Neuroscientists who use MRM-GP learn more about communications and interactions within the brain. This in turn improves understanding of brain functions and disorders.

“Clinically, MRM-GP could enhance diagnostic tools and treatment monitoring by identifying and analyzing neural activity patterns linked to various brain disorders,” said Weihan Li, the study’s lead researcher. 

“Neuroscientists can leverage MRM-GP for its robust modeling capabilities and efficiency in handling large-scale brain data.” 

MRM-GP reveals where and how communication travels across brain regions. 

The group tested MRM-GP using spike trains and local field potential recordings, two kinds of measurements of brain activity. These tests produced representations that illustrated directional flow of communication among brain regions. 

Experiments also disentangled brainwaves, called oscillatory interactions, into organized frequency bands. MRM-GP’s hybrid configuration allows it to model frequencies and phase delays within the latent space of neural recordings.

MRM-GP combines the strengths of two existing methods: the Gaussian process (GP) and linear dynamical systems (LDS). The researchers say that MRM-GP is essentially an LDS that mirrors a GP.

LDS is a computationally efficient and cost-effective method, but it lacks the power to produce representations of the brain. GP-based approaches boost LDS's power, facilitating the discovery of variables in frequency bands and communication directions in the brain.

Converting GP outputs into an LDS is a difficult task in ML. The group overcame this challenge by instilling separability in the model’s multi-region kernel. Separability establishes a connection between the kernel and LDS while modeling communication between brain regions.

Through this approach, MRM-GP overcomes two challenges facing both neuroscience and ML fields. The model helps solve the mystery of intraregional brain communication. It does so by bridging a gap between GP and LDS, a feat not previously accomplished in ML.

“The introduction of MRM-GP provides a useful tool to model and understand complex brain region communications,” said Li, a Ph.D. student in the School of Computational Science and Engineering (CSE). 

“This marks a significant advancement in both neuroscience and machine learning.”

Fellow doctoral students Chengrui Li and Yule Wang co-authored the paper with Li. School of CSE Assistant Professor Anqi Wu advises the group. 

Each MRM-GP student pursues a different Ph.D. degree offered by the School of CSE. W. Li studies computer science, C. Li studies computational science and engineering, and Wang studies machine learning. The school also offers Ph.D. degrees in bioinformatics and bioengineering.

Wu is a 2023 recipient of the Sloan Research Fellowship for neuroscience research. Her work straddles two of the School’s five research areas: machine learning and computational bioscience. 

MRM-GP will be featured at the world’s top conference on ML and artificial intelligence. The group will share their work at the International Conference on Machine Learning (ICML 2024), which will be held July 21-27 in Vienna. 

ICML 2024 also accepted for presentation a second paper from Wu’s group intersecting neuroscience and ML. The same authors will present A Differentiable Partially Observable Generalized Linear Model with Forward-Backward Message Passing.

Twenty-four Georgia Tech faculty from the Colleges of Computing and Engineering will present 40 papers at ICML 2024. Wu is one of six faculty representing the School of CSE who will present eight total papers.

The group’s ICML 2024 presentations exemplify Georgia Tech’s focus on neuroscience research as a strategic initiative.  

Wu is an affiliated faculty member with the Neuro Next Initiative, a new interdisciplinary program at Georgia Tech that will lead research in neuroscience, neurotechnology, and society. The University System of Georgia Board of Regents recently approved a new neuroscience and neurotechnology Ph.D. program at Georgia Tech. 

“Presenting papers at international conferences like ICML is crucial for our group to gain recognition and visibility, facilitates networking with other researchers and industry professionals, and offers valuable feedback for improving our work,” Wu said. 

“It allows us to share our findings, stay updated on the latest developments in the field, and enhance our professional development and public speaking skills.”

Visit https://sites.gatech.edu/research/icml-2024 for news and coverage of Georgia Tech research presented at ICML 2024.

From weather prediction to drug discovery, math powers the models used in computer simulations. To help these vital tools with their calculations, global experts recently met at Georgia Tech to share ways to make math easier for computers.

Tech hosted the 2024 International Conference on Preconditioning Techniques for Scientific and Industrial Applications (Precond 24), June 10-12. 

Preconditioning accelerates matrix computations, a kind of math used in most large-scale models. These computer models become faster, more efficient, and more accessible with help from preconditioned equations.

“Preconditioning transforms complex numerical problems into more easily solved ones,” said Edmond Chow, a professor at Georgia Tech and co-chair of Precond 24’s local organization and program committees. 

“The new problem wields a better condition number, giving rise to the name preconditioning.”

Researchers from 13 countries presented their work through 20 mini-symposia and seven invited talks at Precond 24. Their work showcased the practicality of preconditioners. 

Vandana Dwarka, an assistant professor at Delft University of Technology, shared newly developed preconditioners for electromagnetic simulations. This technology can be used in further applications ranging from imaging to designing nuclear fusion devices.

Xiaozhe Hu presented a physics-based preconditioner that simulates biophysical processes in the brain, such as blood flow and metabolic waste clearance. Hu brought this research from Tufts University, where he is an associate professor.

Tucker Hartland, a postdoctoral researcher at Lawrence Livermore National Laboratory, discussed preconditioning in contact mechanics. This work improves the modeling of interactions between physical objects that touch each other. Many fields stand to benefit from Hartland’s study, including mechanical engineering, civil engineering, and materials science.

A unique aspect of this year’s conference was an emphasis on machine learning (ML). Between a panel discussion, tutorial, and several talks, experts detailed how to employ ML for preconditioning and how preconditioning can train ML models.

Precond 24 invited seven speakers from institutions around the world to share their research with conference attendees. The presenters were: 

• Monica Dessole, CERN, Switzerland
• Selime Gurol, CERFACS, France
• Alexander Heinlein, Delft University of Technology, Netherlands
• Rui Peng Li, Lawrence Livermore National Laboratory, USA 
• Will Pazner, Portland State University, USA 
• Tyrone Rees, Science and Technology Facilities Council, UK
• Jacob B. Schroder, University of New Mexico, USA

Along with hosting Precond 24, several Georgia Tech researchers participated in the conference through presentations. 

Ph.D. students Hua Huang and Shikhar Shah each presented a paper on the conference’s first day. Alumnus Srinivas Eswar (Ph.D. CS 2022) returned to Atlanta to share research from his current role at Argonne National Laboratory. Chow chaired the ML panel and a symposium on preconditioners for matrices.

“It was an engaging and rewarding experience meeting so many people from this very tight-knit community,” said Shah, who studies computational science and engineering (CSE). “Getting to see talks close to my research provided me with a lot of inspiration and direction for future work.”

Precond 2024 was the thirteenth meeting of the conference, which occurs every two years. 

The conference returned to Atlanta this year for the first time since 2005. Atlanta joins Minneapolis as one of only two cities in the world to host Precond more than once. Precond 24 marked the sixth time the conference met in the U.S. 

Georgia Tech and Emory University’s Department of Mathematics organized and sponsored Precond 24. The U.S. Department of Energy Office of Science co-sponsored the conference with Tech and Emory. 

Georgia Tech entities swarmed together in support of Precond 24. The Office of the Associate Vice President for Research Operations and Infrastructure, College of Computing, and School of CSE co-sponsored the conference.

“The enthusiasm at the conference has been very gratifying. So many people organized sessions at the conference and contributed to the very strong attendance,” Chow said. 

“This is a testament to the continued importance of preconditioning and related numerical methods in a rapidly changing technological world.”

A team’s success in any competitive environment often hinges on how well each member can anticipate the actions of their teammates.

Assistant Professor Christopher MacLellan thinks teachable artificial intelligence (AI) agents are uniquely suited for this role and make ideal teammates for video gamers.

With the help of funding from the U.S. Department of Defense, MacLellan hopes to prove his theory with a conversational, task-performing agent he co-engineered called the Verbal Apprentice Learner (VAL).

“You need the ability to adapt to what your teammates are doing to be an effective teammate,” MacLellan said. “We’re exploring this capability for AI agents in the context of video games.” 

Unlike generative AI chatbots like ChatGPT, VAL uses an interactive task-learning approach. 

“VAL learns how you do things in the way you want them done,” MacLellan said. “When you tell it to do something, it will do it the way you taught it instead of some generic random way from the internet.”

A key difference between VAL and a chatbot is that VAL can perceive and act within the gaming world. A chatbot, like ChatGPT, only perceives and acts within the chat dialog.

MacLellan immersed VAL into an open-sourced, simplified version of the popular Nintendo cooperative video game Overcooked to discover how well the agent can function as a teammate. In Overcooked, up to four players work together to prepare dishes in a kitchen while earning points for every completed order.

How Fast Can Val Learn?

In a study with 12 participants, MacLellan found that users could often correctly teach VAL new tasks with only a few examples.

First, the user must teach VAL how to play the game. Knowing that a single human error could compromise results, MacLellan designed three precautionary features:

• When VAL receives a command such as "cook an onion," it asks clarifying questions to understand and confirm its task. As VAL continues to learn, clarification prompts decrease.
• An “undo” button to ensure users can reverse an errant command.
• VAL contains GPT subcomponents to interpret user input, allowing it to adapt to ambiguous commands and typos. The GPT subcomponents drive changes in VAL’s task knowledge, which it uses to perform tasks without additional guidance.

The participants in MacLellan’s study used these features to ensure VAL learned the tasks correctly. 

The high volume of prompts creates a more tedious experience. Still, MacLellan said it provides detailed data on system performance and user experience. That insight should make designing a more seamless experience in future versions of VAL possible.

The prompts also require the AI to be explainable.

“When VAL learns something, it uses the language model to label each node in the task knowledge graph that the system constructs,” MacLellan said. “You can see what it learned and how it breaks tasks down into actions.”

Beyond Gaming

MacLellan’s Teachable AI Lab is devoted to developing AI that inexperienced users can train.

“We are trying to come up with a more usable system where anyone, including people with limited expertise, could come in and interact with the agent and be able to teach it within just five minutes of interacting with it for the first time,” he said.

His work caught the attention of the Department of Defense, which awarded MacLellan multiple grants to fund several of his projects, including VAL. The possibilities of how the DoD could use VAL, on and off the battlefield, are innumerable.

“(The DoD) envisions a future in which people and AI agents jointly work together to solve problems,” MacLellan said. “You need the ability to adapt to what your teammates are doing to be an effective teammate.

“We look at the dynamics of different teaming circumstances and consider what are the right ways to team AI agents with people. The key hypothesis for our project is agents that can learn on the fly and adapt to their users will make better teammates than those that are pre-trained like GPT.”

Design Your Own Agent

MacLellan is co-organizing a gaming agent design competition sponsored by the Institute of Electrical and Electronic Engineers (IEEE) 2024 Conference on Games in Milan, Italy.

The Dice Adventure Competition invites participants to design their own AI agent to play a multi-player, turn-based dungeon crawling game or to play the game as a human teammate. The competition this month and in July offers $1,000 in prizes for players and agent developers in the top three teams.