Kevin Swersky

I try to maintain a broad set of interests within machine learning, although I specialize in deep learning. Most recently, I have become interested in Bayesian optimization for automatically tuning the meta-parameters of neural networks (and other machine learning models). This approach has already had tremendous success on several benchmark datasets and often out-performs experts in tuning these models. I think this is a promising avenue for making deep learning more accessible, both within the machine learning community and beyond.