Why should I care?

Proportion and share of sequences of different SARS-CoV-2 variants in Germany. The variants with the N501Y mutation (e.g. red one) are alert variants with increased infectivity. Source.

The first quarter of 2021 has brought us common knowledge about the importance of genomic sequencing for battling COVID-19. Apparently, monitoring SARS-CoV-2 variants and mutations in countries will be crucial to epidemy spread, vaccine development, and efficiency. There is a well-written sequence of interesting news on this topic in Nature:

| 01–07 Could new COVID variants undermine vaccines? …


Are explainability methods black-box themselves?

There are various adversarial attacks on machine learning models; hence, ways of defending, e.g. by using Explainable AI methods. Nowadays, attacks on model explanations come to light, so does the defense to such adversary. Here, we introduce fundamental concepts related to the domain. A further reference list is available at https://github.com/hbaniecki/adversarial-explainable-ai.

When considering an explanation as a function of model and data, there is a possibility to change one of these variables to achieve a different result.

Attack on explanation via data change


How to tell a good story?

Previous part: Data Visualization Cheat Sheets

Never would have thought that teaching the Data Visualization Techniques course for second-year Data Science students at the Warsaw University of Technology would bring me so much satisfaction. In the second project, we asked students to prepare posters concerning COVID-19 statistics, while also exploring various topics like restrictions, tourism, air pollution, economy, etc.

There were many impressive visualizations, and here are the best results (more can be found at GitHub).

PDF

How to make a good graph?

I have an opportunity to co-teach a Data Visualization Techniques course for second-year Data Science students at the Warsaw University of Technology.
As a part of the course, we asked students to prepare informative posters concerning good plotting practices and specific cheat sheets for data visualization.

The subject of the project was rather open, and here are the best results (more can be found at GitHub).

PDF

I will showcase how straightforward and convenient it is to explain a tensorflow predictive model using the dalex Python package. The introduction to this topic can be found in Explanatory Model Analysis: Explore, Explain, and Examine Predictive Models. For any inquiries, please contact me on LinkedIn or GitHub.

For this example, we will use the data from the World Happiness Report and predict the happiness scored according to economic production, social support, etc. for any given country.

Hubert Baniecki

Explainable machine learning, responsibility, robustness, and adversarial attacks. Developing open-source Python & R packages.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store