So in theory, with XAI methods and the right know-how, even complex black-box models can be at least partially interpreted. But how does it look in reality? In many projects or use cases, interpretability is an important pillar of the overall success. Security aspects, lack of trust in the model results, possible future regulations as well as ethical concerns ensure the need for interpretable ML models.
Tech Deep Dive
With Automized Machine Learning (Auto ML) on the rise – is there still a need for human data scientists?
In short, the answer is yes. Automated Machine Learning (Auto ML) does not make Data Scientists redundant. Rather, it is a useful tool that increases their productivity. The greatest benefit comes when data scientists use Auto ML tools to...
How to deal with missing values
Methods of imputation and when to use them Why missing values should interest us In our work as Data Scientists we often work with time series data and applications for forecasts (=forecasting). As with all "classic"...
The Effect of Corrupt Labels on Computer Vision Performance
An Empirical Study with High Relevance in Medical AI Applications Find all data of this study here. Abstract Whether it's X-rays of lungs or images of the eyeball - medical data sets are never perfect. A small number of misdiagnoses are often accompanied by a much...
Trust in Autonomous Driving
How text explanations help build trust in autonomous systems To "drive" a car that steers itself, or to share the road with autonomous vehicles - what sounds like a dream come true for technology fanatics and visionaries, seems like a dream come true in the eyes of...
The future in e-commerce - with AI to automated product descriptions
Writing product descriptions is time-consuming - especially for providers who have a very large product portfolio. However, in order to be successful in online sales, these descriptive texts are extremely important.
Feature Stores - An Overview
From time to time, a new software system appears on the horizon of the technology landscape. In this paper we look at such a new data access and processing layer: the feature store. It will play an important role in the construction of intelligent systems based on machine learning (ML) algorithms.
Building A Recipe Recommender System For the Thermomix on Cookidoo - Part 2
In Part 1, I introduced you to the challenge of personalized recipe recommendations on Cookidoo and covered the Model Selection phase. This article touches on the Candidate Selection and Scoring & Ranking components of our recommender system. I will walk you...
Building A Recipe Recommender System For the Thermomix on Cookidoo - Part 1
The "For You" Section on cookidoo.de, screenshot obtained on 7th December 2021 In the screenshot, you can see some of our personalized recommendations on Cookidoo, the recipe platform for the smart cooking device Thermomix. In this post, I want to provide you with...
Second Generation Data Lakes: Architectural Principles and Technologies
This article was first published as a cover story in the magazine BI-Spektrum (issue 4 / 2021) under the headline "Data Lakes of the second generation". As a central element of a data-driven organisation, many companies rely on the development of...