Interaction between Model based Signal and Image processing, Machine Learning and Arti cial Intelligence

Published：2019-11-22

Speaker: Ali Mohammad-Djafari

Time and Date: 10:00 am, November 22, 2019

Place: Room B415 of Computing Center Building, Handan Campus, Fudan University

Abstract:

Signal and image processing has always been the main tools in many area and in particular in Medical and Biomedical applications. Nowadays, there are great number of toolboxes, general purpose and very specialized, in which, classical and advanced techniques are implemented and can be used: all the transformation based methods (Fourier, Wavelets, Radon, Abel, ... and much more) as well as all the Model Based and iterative regularization methods. Statistical methods have also shown their success in some area when parametric models are available.

Bayesian inference based methods had great success, in particular, when the data are noisy, uncertain, some missing and some outliers and where there is a need to account and to quantify uncertainties.

In some applications, nowadays, we have more and more data. To use these "Big Data" to extract more knowledge, the Machine Learning and Articial Intelligence tools have shown success and became mandatory. However, even if in many domains of Machine Learning such as classication and clustering these methods have shown success, their use in real scientic problems are limited. The main reasons are twofold: First, the users of these tools can not explain the reasons when the are successful and when they are not. The second is that, in general, these tools can not quantify the remaining uncertainties.

Model based and Bayesian inference approach have been very successful in linear inverse problems. However, adjusting the hyperparameters is complex and the cost of the computation is high. The Convolutional Neural Networks (CNN) and Deep Learning (DL) tools can be useful for pushing farther these limits. At the other side, the Model based methods can be helpful for the selection of the structure of CNN and DL which are crucial in ML success.

In this work, first I give an overview and a survey of the aforementioned methods and explore the possible interactions between them.