| Jeudi 21 Mar 2019 18:30 - Jeudi 21 Mar 2019 20:00 | Gratuit |
|
|
Événement
An ICERM Public Lecture: Bias in Bios: Fairness in a High-stakes Machine-learning Setting
Thursday, March 21, 2019
Brown University Salomon Center
Doors open: 6:00 pm
Lecture begins: 6:30 pm
MEMBERS OF THE COMMUNITY ARE INVITED to attend this public lecture. Machine learning algorithms form biases, like humans, based on the data they observe. However, unlike humans, the algorithms can readily admit their biases when probed appropriately. Using publicly available lists of names, we enumerate biases in an unsupervised fashion from word embeddings trained on public data. Gender, racial, and religious biases emerge, among others. We then analyze the effects of these biases on a problem motivated by recommending jobs to candidates. To collect data for this task, we extract hundreds of thousands of third-person bios from the web. The straightforward application of machine learning is found to amplify some biases. However, unlike humans, it is easy to put in place algorithmic corrections to mitigate this bias amplification.
ABOUT THE SPEAKER: Adam Tauman Kalai received his BA from Harvard and MA and PhD under the supervision of Avrim Blum from CMU. After an NSF postdoctoral fellowship at M.I.T. with Santosh Vempala, he served as an assistant professor at the Toyota Technological Institute at Chicago and then at Georgia Tech. He is now a Principal Researcher at Microsoft Research New England. His honors include an NSF CAREER award and an Alfred P. Sloan fellowship. His research focuses on Artificial Intelligence and Machine Learning algorithms.
This event is free and open to the public.
Limited seating. Please register to reserve a seat.
Hosted by the Institute for Computational and Experimental Research in Mathematics (ICERM).
|
|
 |
AdresseBrown University's Salomon Center (Afficher)
79 Waterman Street
Providence, RI 02912
United States
Catégories
| Chiens bienvenus : Non |
| Non-fumeur : Oui |
| Accessible aux fauteuils roulants : Oui |
|
Contact
|
