ACM Professor Talk Series: Dr. Aylin Caliskan, "Bias in Machine Learning"

Friday, October 12
12:30 – 1:30 pm
Tompkins Hall, 301

ACM talks

GW ACM is hosting a professor talk with Dr. Aylin Caliskan, a new professor at GW! Dr. Caliskan will be talking about her research on discrimination and unfairness in machine learning, as well as strategies to mitigate these biases. Light refreshments will be provided.

Machine learning models are used for applications that affect billions of people every day. Given the enormous and unavoidable effect of machine learning algorithms on individuals and society, we attempt to uncover implicit bias embedded in machine learning models, focusing particularly on word embeddings. We show empirically that natural language necessarily contains human biases, and the paradigm of training machine learning on language corpora means that AI will inevitably imbibe these biases as well. We look at “word embeddings”, a state-of-the-art language representation used in machine learning, and use them to replicate a wide variety of results from psychology on human bias.