nishnik / Paper-Leaf

Contains the description of various papers I have read or reading
12 stars 0 forks source link

Optnet #7

Open nishnik opened 5 years ago

nishnik commented 5 years ago

Link to paper by Brandon Amos, J. Zico Kolter

They present an optimization problem (think of QP problem) as neural network layer, whose output can be used as an input for another layer (like sense layer). They differentiate the KKT condition to find the gradients required for backpropagation.

These layers encode constraints and complex dependencies between the hidden states that traditional convolutional and fully-connected layers often cannot capture.

Link to oral presentation