Efficient architecture for deep neural networks with heterogeneous sensitivity

no code implementations • 12 Oct 2018 • Hyunjoong Cho, Jinhyeok Jang, Chanhyeok Lee, Seungjoon Yang

Each node in a network is assigned a variable that determines the sensitivity with which it learns to perform a given task.

Facial Expression Recognition Facial Expression Recognition (FER) +3

Deep Asymmetric Networks with a Set of Node-wise Variant Activation Functions

no code implementations • 11 Sep 2018 • Jinhyeok Jang, Hyunjoong Cho, Jaehong Kim, Jaeyeon Lee, Seungjoon Yang

As a result, features learned by the nodes are sorted by the node indices in the order of their importance.