Data Model for Computer Vision Explainability, Fairness, and Robustness

In recent years, there has been a growing interest among researchers in the explainability, fairness, and robustness of Computer Vision models. While studies have explored the usability of these models for end users, limited research has delved into the challenges and requirements faced by researchers investigating these requirements. This study...

A System for Model Diagnosis centered around Human Computation

Machine learning (ML) systems for computer vision applications are widely deployed in decision-making contexts, including high-stakes domains such as autonomous driving and medical diagnosis. While largely accelerating the decision-making process, those systems have been found to suffer from a severe issue of reliability, i.e., they can easily...

Closer or even farther from fairness: An assessment of whether fairness toolkits constrain practitioners with regards to algorithmic harms

To encourage ethical thinking in Machine Learning (ML) development, fairness researchers have created tools to assess and mitigate unfair outcomes. However, despite their efforts, algorithmic harms go beyond what the toolkits currently allow to measure. Through 30 semi-structured interviews, we investigated whether data scientists are...

Who Cares About Fairness: How Background Influences the Way Practitioners Consider Machine Learning Harms

The increasing dangers of unfairness in machine learning (ML) are becoming a frequent subject of discussion, both, in academia and popular media. Recent literature focused on introducing and assessing algorithmic solutions to bias in ML. However, there is a disconnect between these solutions and practitioners' needs. By interviewing 30 ML...

Comparison of the usage of Fairness Toolkits amongst practitioners:AIF360 and Fairlearn

Machine learning is still one of the most rapidly growing fields, and is used in a variety of different sectors such as education, healthcare, financial modeling etc(Jordan and Mitchell 2015). However, along with this demand for machine learning algorithms, there comes a need for ensuring that these algorithms are fair and contain little to no...

Surfacing Differences in Practices When Building Fair Machine Learning Systems with Fairness Toolkits: an Empirical Study

The ability to identify and mitigate various risks and harms of using Machine Learning models in industry is an essential task. Specifically because these may produce harmful outcomes for stakeholders, including unfair or discriminatory results. Due to this there has been substantial research into the concepts of fairness and its metrics, bias...

Characterising AI Weakness in Detecting Personal Data from Images By Crowds

This thesis looks at how to characterize weaknesses in machine learning models that are used for detecting privacy-sensitive data in images with the help of crowdsourcing. Before we can come up with a method to achieve a goal, we first need to make clear what we consider privacy-sensitive data. We took the General Data Protection Regulation ...

FindItOut: a Crowdsourcing Discriminative Tacit Knowledge Elicitation Multiplayer Game using Pictures

Despite the ever-growing advances in artificial intelligence (AI), common sense acquisition and reasoning is still comparingly in their early stages to other fields in AI. To further advance this field, it is necessary to collect large amounts of common sense facts or tacit knowledge to train such AI models. One effective way is to use...

Designing a single player textual GWAP for validating tacit knowledge elicitation from crowds

Machine learning can still make harmful mistakes. A solution would be tacit knowledge. Machine learning needs this type of knowledge to improve. An example of such knowledge that can help make the system draw better logical conclusions would be: if presented with an open fridge, then it could deduct that the food will go bad. Tacit knowledge or...

Designing a Multiplayer Competitive Text-Based Game for Elicitation of Tacit Knowledge About Humor from Crowds of People

Tacit knowledge, unlike explicit knowledge, is not easily codifiable, yet important for machine learning models. This research explores a method to gather tacit knowledge about humor using a simple text-based party game, building on the existing idea of using games to gather tacit knowledge from crowds of people. Players propose prompts, which...

SceneFinder: A collaborative game that collects tacit knowledge from crowds

The manual process of collecting and labelling data required for machine learning tasks is labour-intensive, expensive, and time consuming. In the past, efforts have been made to crowdsource this data by either offering people monetary incentives, or by using a gamified approach where users contribute to databases as a side-effect of playing an...

Swipe for Science: a single-player game designed for collecting discriminative evidence

We introduce Swipe for Science, a single-player mobile game designed for collecting discriminative evidence from crowds. When people play this game, we collect data about how certain concepts are associated with different contexts, which is valuable knowledge for machine learning systems. The main gameplay loop consists of swiping concepts up,...

Global Interpretation of Image Classification Models via SEmantic Feature Analysis (SEFA)

Deep learning models have achieved state-of-the-art performance on several image classification tasks over the past years. Several studies claim to approach or even surpass human-levels of performance when using such models to classify images. However, these architectures are notoriously complex, thus making their interpretation a challenge....