Bias Decay Matters : Improving Large Batch Optimization with Connectivity Sharpness

no code implementations • 29 Sep 2021 • Sungyub Kim, Sihwan Park, Yong-Deok Kim, Eunho Yang

To mitigate this issue, we propose simple bias decay methods including a novel adaptive one and found that this simple remedy can fill a large portion of the performance gaps that occur in large batch optimization.

Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications

7 code implementations • 20 Nov 2015 • Yong-Deok Kim, Eunhyeok Park, Sungjoo Yoo, Taelim Choi, Lu Yang, Dongjun Shin

Although the latest high-end smartphone has powerful CPU and GPU, running deeper convolutional neural networks (CNNs) for complex tasks such as ImageNet classification on mobile devices is challenging.

Learning to Select Pre-Trained Deep Representations with Bayesian Evidence Framework

no code implementations • CVPR 2016 • Yong-Deok Kim, Taewoong Jang, Bohyung Han, Seungjin Choi

We propose a Bayesian evidence framework to facilitate transfer learning from pre-trained deep convolutional neural networks (CNNs).

Transfer Learning