The goal of the meeting is to investigate advances and challenges in learning “good representations” from data, in particular representations that can reduce the complexity of later supervised learning stages. The meeting will gather experts in the field to discuss current and future challenges for the theory and applications of learning representations.
There will be four sessions, each one with a set of talks and a panel discussion:
Session 1: Early Features in Vision
Session 2: Learning Features and Representations
Session 3: Learning Invariances and Hierarchies
Session 4: Beyond Feedforward Architectures
Videos/slides have been made available online on the workshop webpage.
Presentation slides (kindly made available by all participants) are available on the LSCL Website - links to slides are listed next to the relevant talk description.