1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.
Post-Doctoral Position in Machine Learning for Human Machine Trust in Teaming
Compensation: 85K per year + Benefits
Contact for interview (include most recent CV + 3 references contact information) and further information
Shuchin Aeron firstname.lastname@example.org,
Matthias Scheutz Matthias.Scheutz@tufts.edu
Description: Sponsored by AFOSR, a postdoctoral research position is sought in the area of developing machine learning algorithms and methods for estimating cognitive states from a multimodal suite of sensors measuring EEG, ECG, BP, fNIRS, eye-gaze, skin conductance, while performing a simulated or real-world task in conjunction with other workload such as conversation and active communication with a team of human or robots. The project offers a one-of-a-kind opportunity in a multi-disciplinary team setting towards building reliable prediction models for human cognitive states from physiological data, a problem that is central to many human-machine interaction settings.
A major part of the project will center on the use and development of unsupervised and weakly supervised machine learning methods such as contrastive representation learning, and self-attention models, to leverage abundance of unlabeled data while utilizing a few strongly labeled data points to inform various cognitive states that may be present in the data. These challenges are further exacerbated by the presence of anomalies and missing data. Furthermore, to address the unique challenges that center on dealing with human data, it is anticipated that the project will require exploiting novel theory and methods in the areas of Domain Adaptation, Privacy and Fairness, Distributional Robustness, and Feature Selection.
For a list of recent papers (2019-2020) related to the project please visit the Google Scholar profiles of
The postdoctoral fellow will be advised jointly by PI Matthias Scheutz (CS), and Co-PIs Shuchin Aeron (ECE) and Sergio Fantini (BioEngineering) at Tufts. Additionally, the postdoctoral fellow will be exposed to new initiatives at Tufts, namely Tufts TRIPODS https://tripods.tufts.edu, Tufts Data Intensive Science Center (DISC) https://disc.tufts.eduoffering a well-rounded development for the next phase of the career.
Eligibility requirements: PhD (CS, ECE, or BioMedical Engineering) in Information Theory or Statistical Signal Processing or Machine Learning or Applied Mathematics with applications to data science. Efficiency in coding with Python, Ability to communicate with the members of an interdisciplinary team and self-manage the project expectations + report and paper writing.