Vahid Tarokh

Tarokh

Rhodes Family Professor of Electrical and Computer Engineering

Vahid Tarokh’s research is in pursuing new formulations and approaches to getting the most out of datasets. Current projects are focused on representation, modeling, inference and prediction from data such as determining how different people will respond to exposure to certain viruses, predicting rare events from small amounts of data, formulation and calculation of limits of learning from observations, and prediction of a macaque monkey's future actions from its brain waves.

Appointments and Affiliations

  • Rhodes Family Distinguished Professor of Electrical and Computer Engineering
  • Professor of Electrical and Computer Engineering
  • Professor of Mathematics

Contact Information

  • Office Location: Rhodes Information Initiative at Duke, 327 Gross Hall , 140 Science Drive, Durham, NC 27708
  • Office Phone: (919) 660-7594
  • Email Address: vahid.tarokh@duke.edu
  • Websites:

Research Interests

Representation, modeling, inference and prediction from data

Awards, Honors, and Distinctions

  • Member. National Academy of Engineering. 2019

Courses Taught

  • COMPSCI 590: Advanced Topics in Computer Science
  • COMPSCI 675D: Introduction to Deep Learning
  • ECE 280L9: Signals and Systems - Lab
  • ECE 280L: Introduction to Signals and Systems
  • ECE 392: Projects in Electrical and Computer Engineering
  • ECE 493: Projects in Electrical and Computer Engineering
  • ECE 494: Projects in Electrical and Computer Engineering
  • ECE 590: Advanced Topics in Electrical and Computer Engineering
  • ECE 685D: Introduction to Deep Learning
  • ECE 891: Internship
  • ECE 899: Special Readings in Electrical Engineering
  • MATH 493: Research Independent Study

Representative Publications

  • Xu, X; Hasan, A; Elkhalil, K; Ding, J; Tarokh, V, Characteristic Neural Ordinary Differential Equations (2021) [abs].
  • Dong, J; Ren, S; Deng, Y; Khatib, O; Malof, J; Soltani, M; Padilla, W; Tarokh, V, Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural
    Network for Phase Retrieval of Meromorphic Functions
    (2021) [abs].
  • Diao, E; Tarokh, V; Ding, J, Privacy-Preserving Multi-Target Multi-Domain Recommender Systems with
    Assisted AutoEncoders
    (2021) [abs].
  • Le, CP; Dong, J; Soltani, M; Tarokh, V, Task Affinity with Maximum Bipartite Matching in Few-Shot Learning (2021) [abs].
  • Deng, Y; Soltani, M; Ren, S; Padilla, W; Khatib, O; Tarokh, V; Dong, J; Malof, J, Data from: Benchmarking deep learning architectures for artificial electromagnetic material problems (2021) [10.7924/r4jm2bv29] [abs].