Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- abstractJanuary 2019
Towards Emotional Intelligence in Social Robots Designed for Children
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPages 547–548https://doi.org/10.1145/3306618.3314319Social robots are robots designed to interact and communicate directly with humans, following traditional social norms. However, many of these current robots operate in discrete settings with predefined expectations for specific social interactions. In ...
- abstractJanuary 2019
Fairness, Accountability and Transparency in Artificial Intelligence: A Case Study of Logical Predictive Models
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPages 541–542https://doi.org/10.1145/3306618.3314316Machine learning -- the part of artificial intelligence aimed at eliciting knowledge from data and automated decision making without explicit instructions -- is making great strides, with new algorithms being invented every day. These algorithms find ...
- abstractJanuary 2019
Risk Assessments and Fairness Under Missingness and Confounding
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPage 531https://doi.org/10.1145/3306618.3314310Fairness in machine learning has become a significant area of research as risk assessments and other algorithmic decision-making systems are increasingly used in high-stakes applications such as criminal justice, consumer lending, and child welfare ...
- abstractJanuary 2019
Popularity Bias in Ranking and Recommendation
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPages 529–530https://doi.org/10.1145/3306618.3314309Many recommender systems suffer from popularity bias: popular items are recommended frequently while less popular, niche products, are recommended rarely or not at all. However, recommending the ignored products in the "long tail" is critical for ...
- research-articleJanuary 2019
Explanatory Interactive Machine Learning
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPages 239–245https://doi.org/10.1145/3306618.3314293Although interactive learning puts the user into the loop, the learner remains mostly a black box for the user. Understanding the reasons behind predictions and queries is important when assessing how the learner works and, in turn, trust. Consequently, ...
- research-articleJanuary 2019
A Comparative Analysis of Emotion-Detecting AI Systems with Respect to Algorithm Performance and Dataset Diversity
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPages 377–382https://doi.org/10.1145/3306618.3314284In recent news, organizations have been considering the use of facial and emotion recognition for applications involving youth such as tackling surveillance and security in schools. However, the majority of efforts on facial emotion recognition research ...
- research-articleJanuary 2019
IMLI: An Incremental Framework for MaxSAT-Based Learning of Interpretable Classification Rules
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPages 203–210https://doi.org/10.1145/3306618.3314283The wide adoption of machine learning in the critical domains such as medical diagnosis, law, education had propelled the need for interpretable techniques due to the need for end users to understand the reasoning behind decisions due to learning ...
- research-articleJanuary 2019
Mapping Missing Population in Rural India: A Deep Learning Approach with Satellite Imagery
- Wenjie Hu,
- Jay Harshadbhai Patel,
- Zoe-Alanah Robert,
- Paul Novosad,
- Samuel Asher,
- Zhongyi Tang,
- Marshall Burke,
- David Lobell,
- Stefano Ermon
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPages 353–359https://doi.org/10.1145/3306618.3314263Millions of people worldwide are absent from their country's census. Accurate, current, and granular population metrics are critical to improving government allocation of resources, to measuring disease control, to responding to natural disasters, and ...
- research-articleJanuary 2019
Taking Advantage of Multitask Learning for Fair Classification
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPages 227–237https://doi.org/10.1145/3306618.3314255A central goal of algorithmic fairness is to reduce bias in automated decision making. An unavoidable tension exists between accuracy gains obtained by using sensitive information as part of a statistical model, and any commitment to protect these ...
- research-articleJanuary 2019
Balancing the Benefits of Autonomous Vehicles
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPages 181–186https://doi.org/10.1145/3306618.3314237Autonomous vehicles are regularly touted as holding the potential to provide significant benefits for diverse populations. There are significant technological barriers to be overcome, but as those are solved, autonomous vehicles are expected to reduce ...
- research-articleJanuary 2019
Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements
- Alex Beutel,
- Jilin Chen,
- Tulsee Doshi,
- Hai Qian,
- Allison Woodruff,
- Christine Luu,
- Pierre Kreitmann,
- Jonathan Bischof,
- Ed H. Chi
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPages 453–459https://doi.org/10.1145/3306618.3314234As more researchers have become aware of and passionate about algorithmic fairness, there has been an explosion in papers laying out new metrics, suggesting algorithms to address issues, and calling attention to issues in existing applications of ...
- research-articleJanuary 2019
Global Explanations of Neural Networks: Mapping the Landscape of Predictions
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPages 279–287https://doi.org/10.1145/3306618.3314230A barrier to the wider adoption of neural networks is their lack of interpretability. While local explanation methods exist for one prediction, most global attributions still reduce neural network decisions to a single set of features. In response, we ...
- research-articleJanuary 2019
Faithful and Customizable Explanations of Black Box Models
AIES '19: Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and SocietyPages 131–138https://doi.org/10.1145/3306618.3314229As predictive models increasingly assist human experts (e.g., doctors) in day-to-day decision making, it is crucial for experts to be able to explore and understand how such models behave in different feature subspaces in order to know if and when to ...