5 papers
Neural Networks with Activation Networks
Jinhyeok Jang, Jaehong Kim, Jaeyeon Lee +1
This work presents an adaptive activation method for neural networks that exploits the interdependency of features. Each pixel, node, and layer is assigned with a polynomial activa…
Deep Asymmetric Networks with a Set of Node-wise Variant Activation Functions
Jinhyeok Jang, Hyunjoong Cho, Jaehong Kim +2
This work presents deep asymmetric networks with a set of node-wise variant activation functions. The nodes' sensitivities are affected by activation function selections such that…
Doubly Nested Network for Resource-Efficient Inference
Jaehong Kim, Sungeun Hong, Yongseok Choi +1
We propose doubly nested network(DNNet) where all neurons represent their own sub-models that solve the same task. Every sub-model is nested both layer-wise and channel-wise. While…
Auto-Meta: Automated Gradient Based Meta Learner Search
Jaehong Kim, Sangyeul Lee, Sungwan Kim +6
Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and tim…
Continual Learning with Deep Generative Replay
Hanul Shin, Jung Kwon Lee, Jaehong Kim +1
Attempts to train a comprehensive artificial intelligence capable of solving multiple tasks have been impeded by a chronic problem called catastrophic forgetting. Although simply r…