JHU Machine Learning Group

As the first research university in the United States, Johns Hopkins University has long cultivated a fundamentally interdisciplinary culture, fostering collaborations between the different divisions of the university. Our machine learning community reflects that vision by developing new methods in core machine learning topics that can transform a wide range of application domains. We seek to push forward the state of the art in terms of theory, algorithms, models and applications with an eye towards solving the most important challenges of our day.

Machine learning is critical to the future of science, engineering and medicine. These domains
rely more and more on distilling knowledge and insights from digital data, building human-machine collaborations with intelligence machines and relying on machine intelligence to make key decisions. As machine learning researchers, our goal is to understand underlying scientific phenomena and mechanisms, and develop new approaches based on these insights.

Our work spans numerous core areas of machine learning, and we work on applications within robotics, speech and language, bioinformatics, vision, health and medicine, neuroscience, network science, and many others.

People

  • All
  • Computational Biology
  • Graphical Models
  • Health
  • Human-compatible AI
  • Natural Language
  • Network Science
  • Neuroscience
  • Optimization
  • Robotics
  • Speech
  • Trustworthy AI
  • Vision
Raman Arora

Raman Arora

OptimizationSpeech
Department of Computer Science
Optimization Speech
Alexis Battle

Alexis Battle

Computational Biology
Department of Biomedical Engineering
Computational Biology
Rama Chellappa

Rama Chellappa

Vision
Department of Electrical and Computer Engineering Department of Biomedical Engineering
Vision
Mateo Diaz

Mateo Diaz

Optimization
Department of Applied Mathematics and Statistics
Optimization
Mark Dredze

Mark Dredze

SpeechNatural LanguageHealth
Department of Computer Science
Speech Natural Language Health
Jason Eisner

Jason Eisner

Natural Language
Department of Computer Science
Natural Language
Benjamin Grimmer

Benjamin Grimmer

Optimization
Department of Applied Mathematics and Statistics
Optimization
Daniel Khashabi

Daniel Khashabi

Natural Language
Department of Computer Science
Natural Language
Holden Lee

Holden Lee

Optimization
Applied Mathematics and Statistics
Optimization
Anqi (Angie) Liu

Anqi (Angie) Liu

Human-compatible AITrustworthy AI
Department of Computer Science
Human-compatible AI Trustworthy AI
Nicolas Loizou

Nicolas Loizou

Optimization
Department of Applied Mathematics and Statistics
Optimization
Mauro Maggioni

Mauro Maggioni

HealthVision
Department of Applied Mathematics and Statistics
Health Vision
Eric Nalisnick

Eric Nalisnick

HealthTrustworthy AI
Department of Computer Science
Health Trustworthy AI
Michael Oberst

Michael Oberst

Computational BiologyHealth
Department of Computer Science
Computational Biology Health
Luana Ruiz

Luana Ruiz

Graphical ModelsOptimization
Department of Applied Mathematics and Statistics
Graphical Models Optimization
Suchi Saria

Suchi Saria

HealthRobotics
Department of Computer Science
Health Robotics
Ilya Shpitser

Ilya Shpitser

Computational BiologyHealth
Department of Computer Science
Computational Biology Health
Jeremias Sulam

Jeremias Sulam

HealthVision
Department of Biomedical Engineering
Health Vision
Soledad Villar

Soledad Villar

Optimization
Department of Applied Mathematics and Statistics
Optimization
Joshua Vogelstein

Joshua Vogelstein

Network ScienceNeuroscienceVision
Department of Biomedical Engineering
Network Science Neuroscience Vision
Alan Yuille

Alan Yuille

Vision
Department of Computer Science
Vision

Courses

AMS 743: Graphical Models

AMS 835: Topics in Statistical Pattern Recognition

BioStats 751-755: Advanced Methods in Biostatistics I-IV

BioStats 763: Bayesian Methods

CS 476/676: Machine Learning: Data to Models

CS 477/677: Causal Inference

CS 479/679: Representation Learning

CS 775: Statistical Machine Learning

CS 792: Unsupervised Learning: From Big Data to Low-Dimensional Representations

CS 875: Selected Topics in Machine Learning

Math 795: Seminar in Data Analysis

CS 482/682: Deep Learning

CS 779: Machine Learning: Advanced Topics

CS 787: Advanced Machine Learning: Machine Learning for Trustworthy AI

CS 437: Federated Learning & Analytics

EN.601.474: Machine Learning: Learning Theory

Research

As one of the top ranked universities in the world, with world leaders in numerous research areas, we host some of the best and most interesting scientific data, and collaboration is one of JHU’s strong suits. As a result, our diverse machine learning research program spans many topics and domains.

Our cross-departmental community of machine learning faculty works on both general-purpose ML and more domain-specific ML methods.

Academic Programs

Program NameLevel of Study
Applied and Computational Mathematics

Master’s Degree

Post-Master’s Certificate

Applied Mathematics and Statistics

Bachelor’s Degree

Full-Time Master’s Degree

Doctoral

Artificial Intelligence

Master’s Degree

Graduate Certificate

Biomedical Engineering

Bachelor’s Degree

Full-Time Master’s Degree

Doctoral

Computer Science

Bachelor’s Degree

Full-Time Master’s Degree

Doctoral

Computer Science

Master’s Degree

Post-Master’s Certificate

Data Science

Master’s Degree

Post-Master’s Certificate

Electrical and Computer Engineering

Full-Time Master’s Degree

Doctoral

Engineering

Doctoral

Master of Science in Engineering in Robotics

Master’s Degree

Affiliated Centers

Center for Language and Speech Processing

Center for Language and Speech Processing

The Johns Hopkins Center for Language and Speech Processing (CLSP) is an interdisciplinary research and educational center focused on the science and technology of language and speech.

Mathematical Institute for Data Science

Mathematical Institute for Data Science

The Johns Hopkins Mathematical Institute for Data Science is establishing the principles behind the analysis and interpretation of massive amounts of complex data.

Laboratory for Computational Sensing and Robotics

Laboratory for Computational Sensing and Robotics

The Laboratory for Computational Sensing and Robotics (LCSR) is one of the most technologically advanced robotics research centers worldwide, and is an international leader in the areas of medical robotics, autonomous systems, and bio-inspiration.

Institute for Assured Autonomy

Institute for Assured Autonomy

Autonomous systems have become increasingly integrated into all aspects of every person’s daily life. In response, the Johns Hopkins Institute for Assured Autonomy (IAA) focuses on ensuring that those systems are safe, secure, and reliable, and that they do what they are designed to do.

Institute for Computational Medicine

Institute for Computational Medicine

The Institute for Computational Medicine (ICM) uses powerful computational tools to transform the practice of medicine.

Institue for Data Intensive Engineering and Science

Institue for Data Intensive Engineering and Science

IDIES is a team of researchers and engineers actively helping research groups find the best solutions for their big data needs and fill any skill gaps with our broad variety of technical expertise and experience.

Diversity, Inclusion, and Ethics

Johns Hopkins University is deeply committed to the dignity and equality of all persons, regardless of who you are or where you come from. The university has formulated an ambitious Roadmap on Diversity and Inclusion to articulate a shared understanding of the university’s focus and priorities (https://diversity.jhu.edu). Similarly, the Whiting School of Engineering values a diverse and inclusive community (https://engineering.jhu.edu/about/diversity-inclusion/).

The machine learning community’s research mission depends on a diverse and inclusive community. Research requires creativity, innovation, and varying perspectives. Ensuring that these qualities are present in our researchers requires us to have research programs that are accessible to and inclusive of researchers from wide-range and diverse set of backgrounds. We are committed to cultivating a culture that is supportive and welcoming.

Furthermore, awareness of the need for diversity and inclusion is especially critical for our research area since Machine Learning has a long track record of underrepresentation of women and minorities.

Join Us.

Current JHU Community Members

Faculty, students, researchers, etc. are welcome to join our mailing list. Visit https://lists.johnshopkins.edu/ and search for the list name (ml-discuss or ml-announce) to subscribe.

Faculty Jobs

Many of JHU’s relevant departments hold searches for new faculty every year. We suggest you check the website of related departments for more information. 

Graduate Programs

We offer many graduate programs related to machine learning. Please review the list of Academic Programs above.