Asma Ghandeharioun, Ph.D. is a research scientist at the People + AI research team in Google Research. She is working on systems that better interpret humans and are better interpreted by humans. Her previous work spans machine learning interpretability, conversational AI, affective computing, digital health, and, more broadly, human-centered AI. She holds a doctorate and master's degree from MIT and a bachelor's degree from the Sharif University of Technology. She has been trained as a computer scientist/engineer and has research experiences at MIT, Google Research, Microsoft Research, EPFL, and in collaboration with medical professionals from Harvard, renowned hospitals in the Boston area, and abroad.
Some of her favorite past projects include: Generating disentangled interpretations via concept traversals, approximating interactive human evaluation using self-play for open-domain dialog models, interpretability benefits of characterizing sources of uncertainty, estimating depressive symptom severity based on sensor data, and an emotion-aware wellbeing chatbot.
Her work has been published in premier peer-reviewed machine learning and digital health venues such as ICLR, NeurIPS, EMNLP, AAAI, ACII, AISTATS, Frontiers in Psychiatry, and Psychology of Well-being, and has been featured in Wired, Wall Street Journal, and New Scientist.