Timezone: »

 
Leveraging Large Scale Models for Identifying and Fixing Deep Neural Networks Biases
Polina Kirichenko · Reyhane Askari Hemmat · Megan Richards

Fri Jul 28 02:00 PM -- 03:00 PM (PDT) @
in 4th Women in Machine Learning (WiML) Un-Workshop »

In this breakout session the leaders will discuss the following questions and challenges with attendees: ● What are the examples of systematic approaches for using generative and multi-modal models to evaluate and improve robustness of deep neural networks? ● What are the limitations of using generative models in terms of sample quality and diversity? ● What are the challenges with using generative modeling based tools in special domains (e.g. medical) where available data is more limited? ● How do we monitor the biases of generative and multi-modal models themselves?

Author Information

Polina Kirichenko (New York University)
Reyhane Askari Hemmat (Meta, Mila)
Megan Richards

More from the Same Authors