BROADCASTS.com

Published: Jan. 19, 2024, 8:51 a.m.

b'

## Summary

\\n

Hello and welcome back to the Austrian Artificial Intelligence Podcast in 2024.

\\n

\\n

With this episode we start into the third year of the podcast. I am very happy to see that the number of listeners has been growing steadily since the beginning and I want to thank you dear listeners for coming back to the podcast and sharing it with your friends.

\\n

Gabriel is a Bioinformatician at the Austrian Institute of Technology and is going to explain his work on ensemble methods and their application in the medical domain.

\\n

For those not familiar with the term, an Ensemble is a combination of individual base models that are combined with the goal to outperform each individual model.

\\n

So the basic idea is, that one combines multiple models that each have their strength and weaknesses into a single ensemble that in the best case has all the strengths without the weaknesses.

\\n

We have seen one type of ensemble methods in the past. These where homogeneous ensemble methods like federated learning, where one trains the same algorithm multiple times by multiple parties or different subsets of the data, for performance reasons or in order to combine model weights without sharing the training data.

\\n

\\n

Today, Gabriel will talk about heterogeneous ensembles that are a combination of different models types and their usage in medical applications. He will explain how one can use them to increase the robustness and the accuracy of predictions. We will discuss how to select and create compositions of models, as well how to combine the different predictions of the individual base models in smart ways that improve their accuracy over simply methods like averaging over majority voting.

\\n

\\n

## AAIP Community

\\n

Join our discord server and ask guest directly or discuss related topics with the community.

\\n

https://discord.gg/5Pj446VKNU

\\n

\\n

## TOC

\\n

00:00:00 Beginning

\\n

00:03:31 Guest Introduction

\\n

00:06:40 Challenges of applying AI in medical applications

\\n

00:17:56 Homogeneous Ensemble Methods

\\n

00:25:50 Combining base model predictions

\\n

00:40:14 Composing Ensembles

\\n

00:45:57 Explainability of Ensemble Methods

\\n

\\n

## Sponsors

\\n

- Quantics: Supply Chain Planning for the new normal - the never normal - https://quantics.io/

\\n

- Belichberg GmbH: Software that Saves the Planet: The Future of Energy Begins Here - https://belichberg.com/

\\n

\\n

## References

\\n

Gabriel Alexander Vignolle - https://www.linkedin.com/in/gabriel-alexander-vignolle-385b141b6/

\\n

Publications - https://publications.ait.ac.at/en/persons/gabriel.vignolle

\\n

Molecular Diagnostics - https://molecular-diagnostics.ait.ac.at/

'