Learning a regularisation functional
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Ollie McEnteggart.
In the light of the immense success of artificial neural networks in machine learning computer vision, hopes have been raised that these methods applied to inverse problems could also lead to better performance. We discuss the limitations of existing algorithms for deep learning in inverse problems and then consider the approach of training a neural network as a regularisation functional. We will propose a new algorithm that relies on recent advances in generative modelling using adversarial networks. We analyse theoretical properties of this algorithm and present first computational results.
This talk is part of the Cambridge Analysts' Knowledge Exchange series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|