Brain Informatics 2022 – My oral communication

Ever wondered how to quantitatively compare feature importance produced by Machine Learning algorithms?

In this new work presented at the Brain Informatics 2022, we introduce the Rank-Biased Overlap (RBO) as similarity measure for comparing rankings of features ordered by their importance. We used the automatic classification of Parkinson’s disease as case study.

Take a look at my recording if you are curious!

Special Session XAIB – Brain Informatics Congress 2021

https://www.bi2021.org
THE 14TH INTERNATIONAL CONFERENCE ON BRAIN INFORMATICS 2021

SPECIAL SESSION ON 

EXPLAINABLE ARTIFICIAL INTELLIGENCE FOR UNVEILING THE BRAIN: FROM THE BLACK-BOX TO THE GLASS-BOX (XAIB)

Half Day

+++++ CALL FOR PAPERS AND ABSTRACTS +++++

Nowadays, Artificial Intelligence (AI) and Machine Learning (ML) are widely used for the exploration of the Brain and their application ranges from the processing and analysis of neuroimages to the automatic diagnosis of the neurodegenerative diseases. However, without an explanation of the ML findings, the automatic medical and clinical decisions are still hard to be trusted. Indeed, the black-box nature of most algorithms, although providing high accuracy, makes the interpretation of the predictions not immediate. Thus, in recent years the need of interpretable and explainable AI, especially in Healthcare, got stronger, as well as the need of glass-box models able to show a trade-off between intelligibility and optimal performance.

The aim of this Special Session is to collect scientific works devoted to the new challenge of Explainable Artificial Intelligence applied on Neuroscience, Neuroimaging and Neuropsychological data for unveiling the Brain. Researchers are encouraged to submit high quality papers or abstracts on novel or state-of-the-art intelligible, interpretable, and understandable AI approaches, such as post-hoc explainability techniques both model-agnostic (e.g., lime, shap) and model-specific (e.g., CNN, SVM, Random Forests), and transparent models (i.e., linear/logistic regression, decision trees, GAM), with special attention to global and local explanations. Systematic reviews and meta-analyses are also welcome.

F1000: a nice place for sharing scientific presentations and posters

During the Neuroinformatics conference in Leiden, just few days ago, I’ve discovered this new web site F1000, where you can upload (for free) your scientific resources.

For example, I’ve added the poster on K-Surfer I’ve presented at that conference.

Well, I can only say that it is a nice site, I’ve not used it enough for a more enthusiastic comment 😀

 

Waiting for the MICCAI 2014

I’m going to leave for Boston in few days, and I’m really excited ’cause I’ll present my new work on advanced feature selection at the MIT!

The MIT, a place I’ve only dreamed on 🙂 

Anyway, my work has been accepted at the MICCAI 2014, in the contest of the CADDementia challenge.

If you want more details about my algorithm, I’m writing the official wiki page of the competition.

The 2014 International Conference on Brain Informatics and Health

A couple of weeks ago, I went to Warsaw for the BIH 2014. Wonderful city, friendly people and tasty food!

I’ve presented my novel (and cool 😀 ) KNIME plugin, K-Surfer during the Special Session on Neuroimaging Data Processing Strategies.

I really appreciated the talks, especially the Prof. Holzinger‘s one. He’s a great speaker with a special humor 🙂

By the way, as usual, during my talk, they took horrible pictures of me handling the microphone like an ice cream -_-“

 

P.S. A part from the conference, I returned a child visiting the Copernicus Museum of Science!