Fairness, Accountability, and Transparency in Machine Learning: Part Two
Fairness, Accountability and Transparency in Machine Learning
November 18, 2016
Presented By: Google, Microsoft, the National Science Foundation, Data Transparency Lab, NYU Information Law Institute, and NYU Technology Law and Policy Institute
0:00 - Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings – Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, and Adam Kalai
32:20 - Semantics Derived Automatically from Language Corpora Necessarily Contain Human Biases – Aylin Caliskan-Islam, Joanna J. Bryson, and Arvind Narayanan
1:08:30 - How to be Fair and Diverse? – L. Elisa Celis, Amit Deshpande, Tarun Kathuria, and Nisheeth Vishnoi
1:28:30 - Exploring or Exploiting? Social and Ethical Implications of Autonomous Experimentation in AI – Sarah Bird, Solon Barocas, Fernando Diaz, Hanna Wallach, and Kate Crawford
1:48:10 - Rawlsian Fairness for Machine Learning – Matthew Joseph, Michael Kearns, Jamie Morgenstern, Seth Neel, and Aaron Roth
Fairness, Accountability and Transparency in Machine Learning
November 18, 2016
Presented By: Google, Microsoft, the National Science Foundation, Data Transparency Lab, NYU Information Law Institute, and NYU Technology Law and Policy Institute
0:00 – Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings – Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, and Adam Kalai
32:20 – Semantics Derived Automatically from Language Corpora Necessarily Contain Human Biases – Aylin Caliskan-Islam, Joanna J. Bryson, and Arvind Narayanan
1:08:30 – How to be Fair and Diverse? – L. Elisa Celis, Amit Deshpande, Tarun Kathuria, and Nisheeth Vishnoi
1:28:30 – Exploring or Exploiting? Social and Ethical Implications of Autonomous Experimentation in AI – Sarah Bird, Solon Barocas, Fernando Diaz, Hanna Wallach, and Kate Crawford
1:48:10 – Rawlsian Fairness for Machine Learning – Matthew Joseph, Michael Kearns, Jamie Morgenstern, Seth Neel, and Aaron Roth
