3 papers
cs.LG2019
DEEP-BO for Hyperparameter Optimization of Deep Networks
Hyunghun Cho, Yongjin Kim, Eunjung Lee +3
The performance of deep neural networks (DNN) is very sensitive to the particular choice of hyper-parameters. To make it worse, the shape of the learning curve can be significantly…
cs.LG2018
Statistical Characteristics of Deep Representations: An Empirical Investigation
Daeyoung Choi, Kyungeun Lee, Duhun Hwang +1
In this study, the effects of eight representation regularization methods are investigated, including two newly developed rank regularizers (RR). The investigation shows that the s…
cs.LG2018
Utilizing Class Information for Deep Network Representation Shaping
Daeyoung Choi, Wonjong Rhee
Statistical characteristics of deep network representations, such as sparsity and correlation, are known to be relevant to the performance and interpretability of deep learning. Wh…