FIX: Fixes broken link and duplicated FINTA reference

posts/2024/2024_08_22_inigo_final_report.rst

@@ -95,16 +95,16 @@ The objective of the project is to generate synthetic human tractograms with tun
 |modified-objectives-title|
 ---------------------------
 
-* Investigate the use of Variational AutoEncoders (VAE) for unconditional tractogram generation based on the GESTA architecture.
-* Investigate the use of Conditional Variational AutoEncoders (CVAE) for conditional tractogram generation based on the GESTA architecture.
+* Investigate the use of Variational AutoEncoders (VAE) for unconditional tractogram generation based on the FINTA architecture.
+* Investigate the use of Conditional Variational AutoEncoders (CVAE) for conditional tractogram generation based on the FINTA architecture.
 * Investigate the possibility to condition the tractogram generation on the fiber bundle for additional control over the process and the data generation, using Adversarial AutoEncoders with attribute-based regularization.
 
 |objectives-completed-title|
 ----------------------------
 
 * **Literature Review on synthetic tractography generation using AutoEncoders**. Main inspirations: 
 
-  * The `FINTA <https://10.1016/j.media.2021.102126>`_ and `FINTA <https://doi.org/10.1016/j.media.2021.102126>`_ papers because they provide a relatively simple AE architecture with an open source sampling algorithm, easy to reuse.
+  * The `FINTA <https://doi.org/10.1016/j.media.2021.102126>`_ and `GESTA <https://doi.org/10.1016/j.media.2023.102761>`_ papers because they provide a relatively simple AE architecture with an open source sampling algorithm, easy to reuse.
 
   * `Variational AutoEncoders for Regression <https://doi.org/10.1007/978-3-030-32245-8_91>`_, which provided a good starting point for conditional Variational AutoEncoders with direct application to brain aging, related to the project's objectives.