Implicit deep learning and robustness

Despite impressive performance, most deep learning models used in AI applications still suffer from a lack of robustness against adversarial attacks. I will describe a new framework for deep learning called implicit deep learning, which generalizes the standard recursive rules of feedforward neural networks. These models are based on the solution of a fixed-point equation involving a single a vector of hidden features, which is thus only implicitly defined. The new framework greatly simplifies the notation of deep learning, and opens up many new possibilities, in terms of novel architectures and algorithms, and robustness analysis and design.
Who is this presentation for?
Data scientists and product managers
Prerequisite knowledge:
Familiarity with deep learning
What you'll learn?
learn about robustness in deep learning

Laurent El Ghaoui is Professor in EECS and IEOR at UC Berkeley and member of the Berkeley Artificial Intelligence Research Lab. He teaches Financial Data Science within the Masters of Financial Engineering at the Haas School of Business. In 2016 he co-founded Kayrros S.A.S., a company that delivers physical asset information for the energy markets from various sources such as satellite imagery; in 2018 he co-founded sumup.ai, which provides high-speed streaming text analytics for enterprise applications.