Author name cluster

Youngmin Lee

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

2 author rows

ICML Conference 2019 Conference Paper

Ladder Capsule Network

Taewon Jeong
Youngmin Lee
Heeyoung Kim

We propose a new architecture of the capsule network called the ladder capsule network, which has an alternative building block to the dynamic routing algorithm in the capsule network (Sabour et al. , 2017). Motivated by the need for using only important capsules during training for robust performance, we first introduce a new layer called the pruning layer, which removes irrelevant capsules. Based on the selected capsules, we construct higher-level capsule outputs. Subsequently, to capture the part-whole spatial relationships, we introduce another new layer called the ladder layer, the outputs of which are regressed lower-level capsule outputs from higher-level capsules. Unlike the capsule network adopting the routing-by-agreement, the ladder capsule network uses backpropagation from a loss function to reconstruct the lower-level capsule outputs from higher-level capsules; thus, the ladder layer implements the reverse directional inference of the agreement/disagreement mechanism of the capsule network. The experiments on MNIST demonstrate that the ladder capsule network learns an equivariant representation and improves the capability to extrapolate or generalize to pose variations.

Details

IJCAI Conference 2016 Conference Paper

Bayesian Nonparametric Collaborative Topic Poisson Factorization for Electronic Health Records-Based Phenotyping

Wonsung Lee
Youngmin Lee
Heeyoung Kim
Il-Chul Moon

Phenotyping with electronic health records (EHR) has received much attention in recent years because the phenotyping opens a new way to discover clinically meaningful insights, such as disease progression and disease subtypes without human supervisions. In spite of its potential benefits, the complex nature of EHR often requires more sophisticated methodologies compared with traditional methods. Previous works on EHR-based phenotyping utilized unsupervised and supervised learning methods separately by independently detecting phenotypes and predicting medical risk scores. To improve EHR-based phenotyping by bridging the separated methods, we present Bayesian nonparametric collaborative topic Poisson factorization (BN-CTPF) that is the first nonparametric content-based Poisson factorization and first application of jointly analyzing the phenotye topics and estimating the individual risk scores. BN-CTPF shows better performances in predicting the risk scores when we compared the model with previous matrix factorization and topic modeling methods including a Poisson factorization and its collaborative extensions. Also, BN-CTPF provides faceted views on the phenotype topics by patients' demographics. Finally, we demonstrate a scalable stochastic variational inference algorithm by applying BN-CTPF to a national-scale EHR dataset.

PDF Details