Predicting respiratory motion using online learning of recurrent neural networks for safer lung radiotherapy
An application of UORO to time series forecasting for healthcare in Matlab
Here, I summarize my research article "Prediction of the position of external markers using a recurrent neural network trained with unbiased online recurrent optimization for safe lung cancer radiotherapy", published in "Computer methods and programs in biomedicine" (2022). This is the first work on the application of UORO to treatment-system latency compensation in radiotherapy. I describe its implementation in Matlab and compare its effectiveness with classical methods (e.g., RTRL).
Personal selection of AI research articles
A collection of well-written articles that I enjoyed reading and helped me grow as an AI professional
In this post, I list research papers that have played an important role in AI or influenced my own understanding of the field.
Surviving Peer Review
Handling Tough Comments on Data and SOTA Comparisons
Handling tough feedback in the peer review process can be complex. In this article, I discuss two common challenging comments that are particularly relevant to machine learning research: implementing state-of-the-art methods and validating findings on larger datasets. Understanding why these requests arise and how you can navigate them will help you succeed as a researcher and computer scientist.
Graph-structured data classification based on spectral methods and the generalized likelihood ratio test
An application to Alzheimer's disease diagnosis from PET image data
This article summarizes how Fourier graph analysis can be used in conjunction with the GLRT decision rule for the classification of signals on graphs. This is explained using an application in neurology, as the brain can naturally be represented by a graph whose nodes represent different regions.
