Publications (9)
Learning disentangled latent representations facilitates discovery and design of functional materials
Jaehoon Cha, Tingyao Lu, Matthew Walker +1
The discovery of new materials is often constrained by the need for large labelled datasets or expensive simulations. In this study, we explore the use of Disentangling Autoencoder…
Disentangling Autoencoders (DAE)
Jaehoon Cha, Jeyan Thiyagalingam
Noting the importance of factorizing (or disentangling) the latent space, we propose a novel, non-probabilistic disentangling framework for autoencoders, based on the principles of…
Hierarchical Auxiliary Learning
Jaehoon Cha, Kyeong Soo Kim, Sanghyuk Lee
Conventional application of convolutional neural networks (CNNs) for image classification and recognition is based on the assumption that all target classes are equal(i.e., no hier…
On the Transformation of Latent Space in Autoencoders
Jaehoon Cha, Kyeong Soo Kim, Sanghyuk Lee
Noting the importance of the latent variables in inference and learning, we propose a novel framework for autoencoders based on the homeomorphic transformation of latent variables,…
Emulating CO Line Radiative Transfer with Deep Learning
Shiqi Su, Frederik De Ceuster, Jaehoon Cha +5
Modelling carbon monoxide (CO) line radiation is computationally expensive for traditional numerical solvers, especially when applied to complex, three-dimensional stellar atmosphe…
Large-Scale Location-Aware Services in Access: Hierarchical Building/Floor Classification and Location Estimation using Wi-Fi Fingerprinting Based on Deep Neural Networks
Kyeong Soo Kim, Ruihao Wang, Zhenghang Zhong +4
One of key technologies for future large-scale location-aware services in access is a scalable indoor localization technique. In this paper, we report preliminary results from our…