Optimization of neural networks for deep learning and applications to CT image segmentation

Programa de Doctorat en Matemàtiques i Informàtica ; [eng] During the last few years, AI development in deep learning has been going so fast that even important researchers, politicians, and entrepreneurs are signing petitions to try to slow it down. The newest methods for natural language processing and image generation are achieving results so unbelievable that people are seriously starting to think they can be dangerous for society. In reality, they are not dangerous (at the moment) even if we have to admit we reached a point where we have no more control over the flux of data inside the deep networks. It is impossible to open a modern deep neural network and interpret how it processes the information and, in many cases, explain how or why it gives back that particular result. One of the goals of this doctoral work has been to study the behavior of weights in convolutional neural networks and in transformers. We hereby present a work that demonstrates how to invert 3x3 convolutions after training a neural network able to learn how to classify images, with the future aim of having precisely invertible convolutional neural networks. We demonstrate that a simple network can learn to classify images on an open-source dataset without loss in accuracy, with respect to a non-invertible one. All that with the ability to reconstruct the original image without detectable error (on 8-bit images) in up to 20 convolutions stacked in a row. We present a thorough comparison between our method and the standard. We tested the performances of the five most used transformers for image classification on an open- source dataset. Studying the embedded matrices, we have been able to provide two criteria that can help transformers learn with a training time reduction of up to 30% and with no impact on classification accuracy. The evolution of deep learning techniques is also touching the field of digital health. With tens of thousands of new start-ups and more than 1B $ of investments only in the last year, this field is growing ...