#31 MLMilan: Paradoxes and Adversarial feature adaptation

Dear all,

ML Milan is back after the summer holidays and we will explore Paradoxes in data science and Adversarial domain feature adaptation.
Event will be held in English with our classical format via Zoom platform.

Talk 1: “Paradoxes in Data Science”

Paradoxes are a class of phenomena that arise when, although starting from premises known as true, we derive some sort of logically unreasonable result. As Machine Learning models create knowledge from data, this makes them susceptible to possible cognitive paradoxes between training and testing. In this talk, Pier Paolo Ippolito will walk you through some of the main paradoxes associated with Data Science and how they can be identified.

Pier Paolo Ippolito, SAS Insitute

Pier Paolo Ippolito è un Data Scientist al SAS Institute di Londra e MSc in Intelligenza Artificiale laureato presso l'Università di Southampton. Ha un forte interesse per i progressi dell'IA e le applicazioni di apprendimento automatico. Al di fuori del suo lavoro, è uno scrittore per Towards Data Science e un Kaggle Contributor.

Talk 2: “Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation”

Depth estimation from monocular images is an important task in localization and 3D reconstruction pipelines for bronchoscopic navigation. Various supervised and self-supervised deep learning-based approaches have proven themselves on this task for natural images. However, the lack of labeled data and the bronchial tissue’s feature-scarce texture make the utilization of these methods ineffective on bronchoscopic scenes. In this talk, I will be presenting you the details of our domain-adaptive solution presented in MICCAI 2021.

Mert Karaoglu, ImFusion

Mert works as a Research Engineer at ImFusion. He completed his Master's studies in Biomedical Computing at TU Munich with a thesis about Adversarial Domain Feature Adaptation for Monocular Bronchoscopic Depth Estimation.

Where? Join us on Thursday 21st of October on Zoom ( https://us02web.zoom.us/j/88695713898?pwd=RGk5dktwUGQrL05pMjAwU0k5bUxnQT09 ). The event will start at 18:45 and will finish around 20.00

Meeting ID: 886 9571 3898
Passcode: 935290
One tap mobile
+390200667245,,88695713898#,,,,*935290# Italy
+390694806488,,88695713898#,,,,*935290# Italy