I am mainly interested in the following:

  • probabilistic machine learning,
  • reliable and trustworthy machine learning,
  • explainable AI,
  • uncertainty quantification and model calibration,
  • causal inference and causal machine learning
  • optimization for machine learning
  • signal processing
  • computer vision
  • modeling and processing of time series/signal/image/video/audio/medical data.

Below are more keywords which I find interesting.

Modeling uncertainties

  • Bayesian deep learning,
  • approximate inference,
  • likelihood-free inference,
  • and nonparametric models.

Uncertainty Quantification and Model Calibration

  • Distribution free uncertainty quantification,
  • model calibration.

Explainable AI

  • Gradient based explanations,
  • perturbation based explanations,
  • causal explanations,
  • counterfactual explanations,
  • and so forth.

Causal Inference and Causal Machine Learning

  • Causal inference for machine learning,
  • causal representation learning,
  • machine learning for causal inference,
  • causal discovery.

Optimization Methods for Machine Learning

  • Second order methods,
  • regularization techniques.

Machine Learning Applications

  • Computer vision and image processing,
  • Multimedia search and retrieval,
  • Audio and musical signal processing,
  • Time series prediction, forecasting, etc.,
  • Medical data processing (computer aided diagnosis etc.),
  • remote sensing and hyperspectral imaging.

Signal Processing

  • Time-frequency analysis
  • Signal decomposition