• Publications
  • Influence
Independent Component Analysis
  • S. Choi
  • Computer Science
  • Handbook of Natural Computing
  • 2012
In the independent component (IC) model it is assumed that the p-variate random vector x = Ωz + μ, where μ is a location vector, Ω is a full rank p× p mixing matrix, and z is a p-Variate vector with mutually independent components. Expand
  • 2,349
  • 318
  • PDF
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
We present an attention-based neural network module, the Set Transformer, specifically designed to model interactions among elements in the input set. Expand
  • 138
  • 33
  • PDF
Semi-Supervised Nonnegative Matrix Factorization
We present semi-supervised NMF (SSNMF), where we jointly incorporate the data matrix and the (partial) class label matrix into NMF. Expand
  • 171
  • 32
Blind Source Separation and Independent Component Analysis : A Review
Blind source separation (BSS) and independent component analysis (ICA) are generally based on a wide class of unsupervised learning algorithms and they found potential applications in many areas fromExpand
  • 270
  • 20
  • PDF
Composite Common Spatial Pattern for Subject-to-Subject Transfer
In this paper we present modifications of CSP for subject-to-subject transfer, where we exploit a linear combination of covariance matrices of subjects in consideration. Expand
  • 162
  • 18
Nonnegative Tucker Decomposition
  • Y. Kim, S. Choi
  • Mathematics, Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 17 June 2007
In this paper we consider the Tucker model with nonnegativity constraints and develop a new tensor factorization method, referred to as nonnegative Tucker decomposition (NTD). Expand
  • 151
  • 16
  • PDF
Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace
We propose a meta-learning method that directly optimizes the gradient descent procedure of task-specific learners. Expand
  • 123
  • 13
  • PDF
Convolutional neural networks for human activity recognition using multiple accelerometer and gyroscope sensors
  • Sojeong Ha, S. Choi
  • Computer Science
  • International Joint Conference on Neural Networks…
  • 24 July 2016
We present CNNs (CNN-pf, CNNpff), especially CNN-pff, for human activity recognition to handle multivariate time series data measured at multiple heterogeneous sensors. Expand
  • 112
  • 12
Algorithms for orthogonal nonnegative matrix factorization
  • S. Choi
  • Mathematics, Computer Science
  • IEEE International Joint Conference on Neural…
  • 1 June 2008
In this paper we present simple algorithms for orthogonal NMF, where orthogonality constraints are imposed on basis matrix or encoding matrix, where the goodness-of-fit is minimized. Expand
  • 129
  • 11
  • PDF