Core Machine Learning
Introductory
- BME 491/691: Learning Theory I Reza Shadmehr
- BioStats 644: Statistical Machine Learning: Methods, Theory, and Applications Vadim Zipunnikov
- BioStats 646-649: Essentials of Probability and Statistical Inference I-IV Michael Rosenblum
- BioStats 776: Statistical Computing Hongkai Ji
- CS 475/675: Machine Learning Mark Dredze
- CogSci 371/671: Bayesian Inference Colin Wilson
- CogSci 371/671: Formal Methods in Cognitive Science: Inference Paul Smolensky
- CogSci 372/672: Formal Methods in Cognitive Science: Neural Networks Paul Smolensky
- ECE 412/612: Machine Learning for Signal Processing Najim Dehak
- ECE 447: Introduction to Information Theory and Coding Sanjeev Khudanpur
Advanced
- AMS 743: Graphical Models Laurent Younes
- AMS 835: Topics in Statistical Pattern Recognition Carey Priebe
- BioStats 751-755: Advanced Methods in Biostatistics I-IV Brian Caffo; Thomas Louis; Jeffrey Leek; Ciprian Crainiceanu
- BioStats 763: Bayesian Methods Gary Rosner
- CS 476/676: Machine Learning: Data to Models Suchi Saria
- CS 477/677: Causal Inference Ilya Shpitser
- CS 479/679: Representation Learning Raman Arora
- CS 775: Statistical Machine Learning Raman Arora
- CS 792: Unsupervised Learning: From Big Data to Low-Dimensional Representations Rene Vidal
- CS 875: Selected Topics in Machine Learning Mark Dredze, Suchi Saria, Jason Eisner, Raman Arora
- Math 795: Seminar in Data Analysis Mauro Maggioni; James Murphy
Mathematical, Statistical, and Computational Background
The following courses are good sources for foundational background that is often needed in machine learning.
- AMS 420/620: Introduction to Probability John Wierman
- AMS 430/630: Introduction to Statistics Avanti Athreya
- AMS 433/633: Monte Carlo Methods James Spall
- AMS 692: Matrix Analysis and Linear Algebra Youngmi Hur
- AMS 723: Markov Chains Jim Fill
- AMS 730: Statistical Theory Carey Priebe
- AMS 732: Bayesian Statistics Yanxun Xu
- AMS 737: Distribution-Free Statistics and Resampling Methods Laurent Younes
- AMS 761: Nonlinear Optimization I Daniel Robinson
- AMS 762: Nonlinear Optimization II Daniel Robinson
- AMS 763: Stochastic Search and Optimization James Spall
- AMS 831: Advanced Topics in Bayesian Statistics Yanxun Xu
- BME 616: Introduction to Linear Dynamical Systems Sridevi Sarma
- BioStats 771: Advanced Statistical Theory I Daniel Sharfstein
- BioStats 772: Advanced Statistical Theory II Daniel Sharfstein
- CS 320/620: Parallel Programming Randal Burns
- CS 325/425: Declarative Methods Jason Eisner
- CS 464/664: Randomized Algorithms Rao Kosaraju
- ECE 651: Random Signal Analysis Archana Venkataraman
Beyond these basic courses, JHU offers many relevant advanced courses on prob/stats theory, Markov chains, FFT and wavelet transforms, stochastic processes, discrete and continuous optimization, streaming and parallel algorithms, etc. See the course search engine.
Applied Machine Learning
Biology
- AMS 450: Computational Molecular Medicine Donald Geman
- AMS 735: Topics in Bioinformatics Donald Geman
- BME 487: Foundations of Computational Biology I P Fleming
- BME 488/688: Foundations of Computational Biology & Bioinformatics II Rachel Karchin
- BioStats 638: Analysis of Biological Sequences Sarah Wheelan
- BioStats 656: Multilevel Statistical Models in Public Health Elizabeth Colantuoni
- BioStats 688: Statistics for Genomics Jeffrey Leek; Rafael Irizarry
- BioStats 698: Bioperl J Anderson
- BioStats 841: Protein Bioinformatics F Lebeda; M Olson
- ChemBE 414/614: Protein Structure Prediction and Design Jeffrey Gray
- ECE 610: Computational Genomics M Ermolaeva
Courses on machine learning for biology span the Biostatistics and Bioinformatics programs. Biostatistics is in the Bloomberg School of Public Health, and Bioinformatics is a joint offering of the Zanvyl Krieger School of Arts and Sciences and the Whiting School of Engineering. Besides the ML-oriented courses listed above, there exist many courses for different areas of specialization. A full list of biostatistics courses is here.
Robotics
- CS 336: Algorithms for Sensor-Based Robotics Gregory Hager
- CS 445-446: Computer Integrated Surgery I-II Russ Taylor
- CS 745: Seminar on Computer Integrated Surgery Peter Kazanzides
- MechE 646: Introduction to Robotics Louis Whitcomb
- MechE 647: Adaptive Systems Louis Whitcomb
Robotics research at JHU spans many laboratories, including the Computational Sensing and Robotics Laboratory, the Locomotion in Mechanical and Biological Systems, and the Computer Integrated Interventional Systems Lab. There are many more domain courses listed at the Computer Integrated Surgical Systems and Technology page.
Economics
- Econ 611: Decision Theory Edi Karni
- Econ 614: Mathematical Economics Ali Khan
- Econ 615: Mathematical Methods in Economics I Edi Karni
- Econ 618: Game Theory Hülya Eraslan
- Econ 633: Econometrics Yingyao Hu
Language and Speech
- CS 465/665: Natural Language Processing Jason Eisner
- CS 466: Information Retrieval and Web Agents David Yarowsky
- CS 468/668: Machine Translation Philipp Koehn
- CS 865: Selected Topics in Natural Language Processing Jason Eisner
- CS 866: Selected Topics in Meaning, Translation and Generation of Text Kyle Rawlins; Benjamin Van Durme
- CS 868: Selected Topics in Machine Translation Philipp Koehn
- ECE 315/515: Information Processing of Audio and Visual Signals Hynek Hermansky
- ECE 666: Information Extraction from Speech and Text Sanjeev Khudanpur
- ECE 680: Speech and Auditory Processing by Humans and Machines Hynek Hermansky
- ECE 735: Sensory Information Processing Andreas Andreou
Beyond these ML-oriented courses, language and speech researchers also need domain knowledge. A full spectrum of graduate linguistics courses is offered by JHU’s #1-ranked Cognitive Science Department. It is also worth considering how humans solve language learning and linguistic inference problems, via JHU’s various courses on language acquisition, psycholinguistics, and neurolinguistics.
Vision
- AMS 493/693: Mathematical Image Analysis Nicolas Charon
- APL 443: Real-Time Computer Vision Philippe Burlina; Daniel DeMenthon
- CS 361/461: Computer Vision Gregory Hager
- CS 462: Advanced Topics in Computer Vision Rene Vidal
- CS 485: Probabilistic Models of the Visual Cortex Alan Yuille
- CogSci 814: Research Seminar in Computer Vision Alan Yuille
Vision research at JHU spans many application areas, including robotics, computer assisted surgery, biomedical imaging instrumentation, medical imaging systems, optics, visual perception, and vision neuroscience. For more vision-specific courses in these areas, see the Vision Lab list. See also the list of imaging related courses at the Hopkins Imaging Initiative.