Successes and Misses of Global Health Development: Detecting Temporal Concept Drift of Under-5 Mortality Prediction Models with Bias Scan
- Ifrah Idrees
- Skyler Speakman
- et al.
- 2021
- AMIA Annual Symposium
Dr. Speakman uses Machine Learning and Data Science to impact peoples' lives across the continent of Africa. He is a first line manager of the AI Sciences team at IBM Research Africa (Kenya lab).
The Kenya-based team works on scaling AI by improving the cost/performance of data pipelines and better understanding how data can be represented for multiple downstream tasks.
Previously, the team contributed to Trustworthy AI topics such bias, explainability, causality, and robustness. More specifically, the team approached these problems from the perspective of detecting anomalous subsets of data.
Dr. Speakman received a Ph.D. from Carnegie Mellon University. He was a founding member of the Event & Pattern Detection Lab. Before CMU he earned master degrees in Mathematics and Statistics from the University of Kentucky. He lives in Nairobi, Kenya with his wife and three children.
A tale of adversarial attacks & out-of-distribution detection stories in the activation space