23 citations
- Korea Advanced Institute of Science and TechnologyKR2 papers
- Pohang University of Science and TechnologyKR2 papers
- Busitema UniversityUG1 paper
- Hyundai Mobis (South Korea)KR1 paper
- Korea Research Institute of Standards and ScienceKR1 paper
- Korea University of Science and TechnologyKR1 paper
- Mbarara University of Science and TechnologyUG1 paper
- Norwegian University of Science and TechnologyNO1 paper
- Pohang TechnoPark (South Korea)KR1 paper
- Tongji UniversityCN1 paper
- University of Uyo Teaching HospitalNG1 paper
- Virginia TechUS1 paper
Showing 2019Show all
3 papers · 1 filter
cs.CL2019★ 20 cited
Self-Knowledge Distillation in Natural Language Processing
Sangchul Hahn, Heeyoul Choi
Since deep learning became a key player in natural language processing (NLP), many deep learning models have been showing remarkable performances in a variety of NLP tasks, and in…
cs.CV2019★ 21 cited
Capsule Networks Need an Improved Routing Algorithm
Inyoung Paik, Taeyeong Kwak, Injung Kim
In capsule networks, the routing algorithm connects capsules in consecutive layers, enabling the upper-level capsules to learn higher-level concepts by combining the concepts of th…
cs.CV2019★ 4 cited
Overcoming Catastrophic Forgetting by Neuron-level Plasticity Control
Inyoung Paik, Sangjun Oh, Tae-Yeong Kwak +1
To address the issue of catastrophic forgetting in neural networks, we propose a novel, simple, and effective solution called neuron-level plasticity control (NPC). While learning…