Other Media

• The TWIML AI Podcast; Metric Elicitation and Robust Distributed Learning
  • [web]

Selected Presentations (Healthcare, Neuroscience and Biological Imaging)

• AI for Healthcare [slides (pdf)]

  • (with Applications to the COVID-19 Pandemic) at c3.AI Digital Transfornmation Institute [video] (Sep 2020)
  • (Applications and Challenges) at WCS Explore series [video] (Oct 2020)

• Towards Machine Learning for Personalized Healthcare

  • at Illinois Big Data Summit [slides (pdf)] (Nov 2019)

• Synthesizing fMRI using generative adversarial networks: cognitive neuroscience applications, promises and pitfalls (Tutorial)

  • at Neurohackacademy (U Washington) [video] (Aug 2018)
  • at DALI (Jan 2019)
  • at OHBM Education Course (Presented by Bliss Chapman, June 2019)
  • at IAS [video] (Sep 2020)

• Probabilistic Models for Brain Data Analysis [slides (pdf)]

  • at UC Berkeley (July 2017)
  • at University of Sydney (Aug 2017)
  • short version at Big Data Neuroscience workshop (Sep 2017)

• Time-varying dynamic brain connectivity (Tutorial) [slides (pdf)]

  • at PRNI (Jun 2016)
  • short version at Brainhack@Illinois (Mar 2017)

• Decoding brain activity using a large-scale probabilistic functional-anatomical atlas of human cognition [slides (pdf)]

  • at Beckman cognitive neuroscience brown bag (Oct 2016)
  • at Univ. of Sydney (Aug 2017)

Selected Presentations (Machine Learning)

• Algorithmic Fairness: Why It’s Hard and Why It’s Interesting (With Olga Russakovsky)
  [web] (June 2022)

• Algorithmic fairness and metric elicitation via the geometry of classifier statistics

  • at Harvard ML theory [video] (Nov 2020)

• Towards algorithms for measuring and mitigating ML unfairness
  [slides (pdf)]

  • at Schwartz Reisman Institute for Technology and Society (University of Toronto) [video] (Dec 2020)
  • at Montreal AI Symposium (updated; September 2022)

• Tutorial on Representation Learning and Fairness (with Moustapha Cisse)
  [slides (pdf)]

  • at NeurIPS [video] (Dec 2019)

• Asynchrony and Fault-tolerance in Federated ML; Two Vignettes

  • at Google Seattle (June 2019)

• Probabilistic Models for Brain Data Analysis
  [slides (pdf)]

  • at UC Berkeley (July 2017)
  • at University of Sydney (Aug 2017)
  • short version at Big Data Neuroscience workshop (Sep 2017)

• Robust Federated and Distributed Learning

  • at ITA (Feb 2019)
  • at TTIC (Mar 2019)
  • at IBM Research [slides (pdf)] (Oct 2019)

• Eliciting Machine Learning Metrics

  • at Kavli Frontiers of Science [video] (Feb 2019)

• How effective is your classifier? Revisiting the role of metrics in machine learning

  • at Google Brain (March 2018)
  • at Purdue’s Approximation Theory and Machine Learning workshop [video] (Sep 2018)
  • at Microsoft Research Cambridge [slides (pdf)] [video] (Sep 2019)

• Interpretability … the who, what, why, and how.

  • at Machine Learning Summer School UCL [video (part 1)], [video (part 2)] (July 2019)

• Metrics Matter, Examples from Binary and Multilabel Classification [slides (pdf)]

  • at Google Brain (July 2017)
  • at Facebook AI Research Paris (Aug 2017)
  • at MPI Tuebingen (Aug 2017)

• Learning with Aggregated Data: A Tale of Two Approaches [slides (pdf)]

  • at UW Madison [video] (Oct 2017)
  • at CSL SINE Seminar (March 2017)

• Frequency Domain Predictive Modeling with Aggregated Data [slides (pdf)]

  • at Information Theory and Applications Workshop (Feb 2017)

• Beyond Accuracy: Scalable Classification with Complex Metrics [slides (pdf)]

  • at Georgia Tech (Nov 2016)
  • at Illinois Machine Learning Seminar (Jan 2017)

• From probabilistic models to decision theory and back again

  • at TTIC (June 2016)
  • at Gatsby Unit, UCL [abstract (pdf)], [slides (pdf)] (July 2016)
  • at University of Amsterdam (July 2016)
• Consistency Analysis for Binary Classification Revisited
  • ICML (Aug 2017) [video]