TR2021-016
AutoBayes: Automated Bayesian Graph Exploration for Nuisance-Robust Inference
-
- "AutoBayes: Automated Bayesian Graph Exploration for Nuisance-Robust Inference", IEEE Access, DOI: 10.1109/ACCESS.2021.3064530, Vol. 9, pp. 39955-39972, March 2021.BibTeX TR2021-016 PDF Presentation
- @article{Demir2021mar,
- author = {Demir, Andac and Koike-Akino, Toshiaki and Wang, Ye and Erdogmus, Deniz},
- title = {AutoBayes: Automated Bayesian Graph Exploration for Nuisance-Robust Inference},
- journal = {IEEE Access},
- year = 2021,
- volume = 9,
- pages = {39955--39972},
- month = mar,
- doi = {10.1109/ACCESS.2021.3064530},
- issn = {2169-3536},
- url = {https://www.merl.com/publications/TR2021-016}
- }
,
- "AutoBayes: Automated Bayesian Graph Exploration for Nuisance-Robust Inference", IEEE Access, DOI: 10.1109/ACCESS.2021.3064530, Vol. 9, pp. 39955-39972, March 2021.
-
MERL Contacts:
-
Research Areas:
Artificial Intelligence, Machine Learning, Robotics, Signal Processing
Abstract:
Learning data representations that capture task-related features, but are invariant to nuisance variations remains a key challenge in machine learning. We introduce an automated Bayesian inference framework, called AutoBayes, that explores different graphical models linking classifier, encoder, decoder, estimator and adversarial network blocks to optimize nuisance-invariant machine learning pipelines. AutoBayes also enables learning disentangled representations, where the latent variable is split into multiple pieces to impose various relationships with the nuisance variation and task labels. We benchmark the framework on several public datasets, and provide analysis of its capability for subject-transfer learning with/without variational modeling and adversarial training. We demonstrate a significant performance improvement with ensemble learning across explored graphical models
Related News & Events
-
AWARD MERL Ranked 1st Place in Cross-Subject Transfer Learning Task and 4th Place Overall at the NeurIPS2021 BEETL Competition for EEG Transfer Learning. Date: November 11, 2021
Awarded to: Niklas Smedemark-Margulies, Toshiaki Koike-Akino, Ye Wang, Deniz Erdogmus
MERL Contacts: Toshiaki Koike-Akino; Ye Wang
Research Areas: Artificial Intelligence, Signal Processing, Human-Computer InteractionBrief- The MERL Signal Processing group achieved first place in the cross-subject transfer learning task and fourth place overall in the NeurIPS 2021 BEETL AI Challenge for EEG Transfer Learning. The team included Niklas Smedemark-Margulies (intern from Northeastern University), Toshiaki Koike-Akino, Ye Wang, and Prof. Deniz Erdogmus (Northeastern University). The challenge addresses two types of transfer learning tasks for EEG Biosignals: a homogeneous transfer learning task for cross-subject domain adaptation; and a heterogeneous transfer learning task for cross-data domain adaptation. There were 110+ registered teams in this competition, MERL ranked 1st in the homogeneous transfer learning task, 7th place in the heterogeneous transfer learning task, and 4th place for the combined overall score. For the homogeneous transfer learning task, MERL developed a new pre-shot learning framework based on feature disentanglement techniques for robustness against inter-subject variation to enable calibration-free brain-computer interfaces (BCI). MERL is invited to present our pre-shot learning technique at the NeurIPS 2021 workshop.