Hauptnavigation

Proseminar Wintersemester 2020/2021

Machine Learning

Prof. Dr. Katharina Morik
Informatik LS8


Trustworthy Machine Learning

Machine learning (ML) is a driving force for many successful applications in Artificial Intelligence. Machine learning is not just a class of algorithms but there are long and nested sequences of algorithms and, at the same time, algorithms are built upon other algorithms from libraries or tools. This makes it hard for users to understand machine learning models.
One approach to allowing an understanding of machine learning is to explain the learned model. It has been pointed out that also the data which are used for training the model need a careful inspection. 8 of the selected papers for this seminar deal with explainability. Among them are, of course, those that explain deep neural networks

We want to include no only pure computer science views, but also look at what psychology, sociology and ethics have to say about AI and ML, in particular. A view of the broad area of ethics and bias is represented by 3 carefully selected papers.

Deep neural networks are particularly challenging our understanding. Their function approximation capabilities are so huge that they are hard to understand and control. A comprehensive sound paper on the trustworthiness of deep neural networks is split into three parts, so that three students could study this work. All parts only need the introduction as an additional read, not the other parts.

The impact of learned models on staff selection, sales, and popularity is tremendous. The bias in data lead to a bias in real-world life. Actually, biased data may do harm to the health and success of people. Hence, the community of researchers in machine learning and other disciplines discuss how to establish fairness. 12 papers cover diverse aspects of fairness.

Date: Tuesdays, 14:15 - 16:00 h, online

Moodle Workspace



Topics, literature (excluding books) and dates:

Topic Publications Date
Explainability When People and Algorithms Meet: User-Reported Problems in Intelligent Everyday Applications 17.11.2020
Explainability A Survey of Methods for Explaining Black Box Models 17.11.2020
Explainability Interpreting Classifiers by Multiple Views 17.11.2020
Explainability Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches 24.11.2020
Explainability Datasheets for Datasets 24.11.2020
Explainability Evolutionary Psychology and Artificial Intelligence: The Impact of AI on human behaviour 24.11.2020
Ethics And Bias AI4People - An Ethical Framework for a Good AI Society: Opportunities, Risks, Principles and Recommendations 01.12.2020
Ethics And Bias Semantics Derived Automatically from Language Corpora Contain Human-Like Bias 01.12.2020
Ethics And Bias Wikipedia, Sociology and the Pitfalls of Big Data 01.12.2020
Trustworthy Deep Neural Networks A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attacks and Defence, and Interpretability -- Safety and Verification 08.12.2020
Trustworthy Deep Neural Networks A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attacks and Defence, and Interpretability -- Testing and Adversarial Attack 08.12.2020
Trustworthy Deep Neural Networks A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attacks and Defence, and Interpretability -- Interpretability 08.12.2020
Explainability Methods for Interpreting and Understanding Deep Neural Networks 15.12.2020
Explainability Evaluating the Visualization Of What A Deep Neural Network Has Learned 15.12.2020
Trustworthy Deep Neural Networks Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning 15.12.2020
Fairness Fairness Constraints: A Flexible Approach for Fair Classification 05.01.2021
Fairness Three Naive Bayes Approaches for Discrimination-Free Classification 05.01.2021
Fairness Two-Sided Fairness for Repeated Matchings in Two-Sided Markets: A Case Study of a Ride-Hailing Platform 05.01.2021
Fairness Fairness and Discrimination in Retrieval and Recommendation 12.01.2021
Fairness Equity of Attention: Amortizing Individual Fairness in Rankings 12.01.2021
Fairness Fairness-Aware Ranking in Search and Recommendation Systems with Applications to LinkedIn Talent Search 12.01.2021
Fairness Fa*ir: A Fair Top-k Ranking Algorithm 19.01.2021
Fairness Unbiased Learning-to-Rank with Biased Feedback 19.01.2021
Fairness Fair Learning-to-Rank from Implicit Feedback 19.01.2021
Fairness Fair-by-design Matching 26.01.2021
Fairness Poisoning Attacks on Algorithmic Fairness 26.01.2021