Frederik Hvilshøj

Frederik is the Machine Learning Lead at Encord. He has an extensive computer vision and deep learning background and has completed a Ph.D. in Explainable Deep Learning and Generative Models at Aarhus University, and published research in Efficient Counterfactuals from Invertible Neural Networks and Back-propagation through Fréchet Inception Distance. Before his P.hD., Frederik studied for an M.Sc. in computer science while being a teaching assistant for "Introduction to databases" and "Pervasive computing and Software Architecture."

He also recently led Encord's ML team to release the world's largest multimodal dataset, E-MM1.

Frederik enjoys spending time with his two kids in his spare time and occasionally goes for long hikes around his hometown in the west of Denmark.

You can find him on:

• Google Scholar
• ResearchGate

Publications:

• ECINN: Efficient Counterfactuals from Invertible Neural Networks
• Backpropagating through Fréchet Inception Distance
• What if Neural Networks had SVDs?
• One Reflection Suffice
• MeLIME: Meaningful Local Explanation for Machine Learning Models
• Faster Orthogonal Parameterization with Householder Matrices