 |
|
Theses
Parallélisation de problèmes d'apprentissage par des réseaux neuronaux artificiels. Application en radiothérapie externe
Abstract : This research is about the application of neural networks used in the external radiotherapy domain. The goal is to elaborate a new evaluating system for the radiation dose distributions in heterogeneous environments. The final objective of this work is to build a complete toolkit to evaluate the optimal treatment planning.
My first research point is about the conception of an incremental learning algorithm. The interest of my work is to combine different optimisations specialised in the function interpolation and to propose a new algorithm allowing to change the neural network architecture during the learning phase. This algorithm allows to minimise the final size of the neural network while keeping a good accuracy. The second part of my research is to parallelise the previous incremental learning algorithm. The goal of that work is to increase the speed of the learning step as well as the size of the learned dataset needed in a clinical case. For that, our incremental learning algorithm presents an original data decomposition with overlapping, together with a fault tolerance mechanism.
My last research point is about a fast and accurate algorithm computing the radiation dose deposit in any heterogeneous environment. At the present time, the existing solutions used are not optimal. The fast solution are not accurate and do not give an optimal treatment planning. On the other hand, the accurate solutions are far too slow to be used in a clinical context. Our algorithm answers to this problem by bringing rapidity and accuracy. The concept is to use a neural network adequaltely learned together with a mechanism taking into account the environment changes. The advantages of this algorithm is to avoid the use of a complex physical code while keeping a good accuracy and reasonable computation times.
My first research point is about the conception of an incremental learning algorithm. The interest of my work is to combine different optimisations specialised in the function interpolation and to propose a new algorithm allowing to change the neural network architecture during the learning phase. This algorithm allows to minimise the final size of the neural network while keeping a good accuracy. The second part of my research is to parallelise the previous incremental learning algorithm. The goal of that work is to increase the speed of the learning step as well as the size of the learned dataset needed in a clinical case. For that, our incremental learning algorithm presents an original data decomposition with overlapping, together with a fault tolerance mechanism.
My last research point is about a fast and accurate algorithm computing the radiation dose deposit in any heterogeneous environment. At the present time, the existing solutions used are not optimal. The fast solution are not accurate and do not give an optimal treatment planning. On the other hand, the accurate solutions are far too slow to be used in a clinical context. Our algorithm answers to this problem by bringing rapidity and accuracy. The concept is to use a neural network adequaltely learned together with a mechanism taking into account the environment changes. The advantages of this algorithm is to avoid the use of a complex physical code while keeping a good accuracy and reasonable computation times.
Cited literature [43 references]
https://tel.archives-ouvertes.fr/tel-00260013
Contributor : Marc Sauget <>
Submitted on : Sunday, March 2, 2008 - 8:31:55 PM
Last modification on : Thursday, November 12, 2020 - 9:42:05 AM
Long-term archiving on: : Friday, September 28, 2012 - 10:32:03 AM
Contributor : Marc Sauget <>
Submitted on : Sunday, March 2, 2008 - 8:31:55 PM
Last modification on : Thursday, November 12, 2020 - 9:42:05 AM
Long-term archiving on: : Friday, September 28, 2012 - 10:32:03 AM