Multi-objective problems in machine learning
Jonas and I wrote a blogpost on why some ML algorithms are hard to tune and how to fix it. Read the post here .
Iryna Korshunova
Latest posts
BRUNO: A Deep Recurrent Model for Exchangeable Data
This post gives a short overview of our recent NeurIPS paper: BRUNO: A Deep Recurrent Model for Exchangeable Data by I. Korshunova, J. Degrave, F. Huszár, Y. Gal, A. Gretton, and J. Dambre where we presented a provably exchangeable model whose: predictive distribution \(p(x_n \mid x_{1:n-1})\) is tractable to evaluate and can be sampled from with a linear complexity in the number of data points we…
Lung Cancer Detection
Our team has finished 9th in the third Data Science Bowl competition on Kaggle. Read about our approach here .
Diagnosing Heart Diseases with Deep Neural Networks
The Second National Data Science Bowl , a data science competition where the goal was to automatically determine cardiac volumes from MRI scans, has just ended. We participated with a team of 4 members from Ghent University and finished 2nd! The team kunsthart ( artificial heart in English) consisted of Ira Korshunova , Jeroen Burms , Jonas Degrave , 3 PhD students, and professor Joni Dambre .…
Plankton classification
Our team from Ghent University consisting of Sander, Aaron, Jeroen, Lionel, Pieter, Jonas and myself has won the National Data Science Bowl competition on Kaggle! Read about our solution here .
Predicting epileptic seizures
The American Epilepsy Society Seizure Prediction Challenge ended a few days ago, and I finished 10th out of 504 teams. In this post I will briefly outline the problem and my solution. The problem Epilepsy is one of the most commonly diagnosed neurological disorders. It is characterized by the occurrence of spontaneous seizures, and to make matters even worse nearly 30% of patients cannot control…