T
Taehwan Kim
Researcher at Mitre Corporation
Publications - 7
Citations - 587
Taehwan Kim is an academic researcher from Mitre Corporation. The author has contributed to research in topics: Bounded function & Complex-valued function. The author has an hindex of 7, co-authored 7 publications receiving 534 citations. Previous affiliations of Taehwan Kim include University of Maryland, Baltimore County.
Papers
More filters
Journal ArticleDOI
Approximation by fully complex multilayer perceptrons
Taehwan Kim,Tulay Adali +1 more
TL;DR: Three proofs of the approximation capability of the fully complex MLP are provided based on the characteristics of singularity among ETFs, which shows the output of complex MLPs using ETFs with isolated and essential singularities uniformly converges to any nonlinear mapping in the deleted annulus of singularities nearest to the origin.
Journal ArticleDOI
Fully Complex Multi-Layer Perceptron Network for Nonlinear Signal Processing
Taehwan Kim,Tulay Adali +1 more
TL;DR: A fully complex multi-layer perceptron (MLP) structure that yields a simplified complex-valued back-propagation (BP) algorithm is presented and the advantage of ETFs over split complex AF is shown in numerical examples where nonlinear magnitude and phase distortions of non-constant modulus modulated signals are successfully restored.
Proceedings ArticleDOI
Independent component analysis by complex nonlinearities
TL;DR: A number of complex nonlinear functions are proposed for the independent component analysis of complex-valued data and their efficiency in generating the higher order statistics needed for ICA is shown.
Proceedings ArticleDOI
Complex backpropagation neural network using elementary transcendental activation functions
Taehwan Kim,Tulay Adali +1 more
TL;DR: The fully complex NN design is extended to employ other complex activation functions of the hyperbolic, circular, and their inverse function family to restore the nonlinear amplitude and phase distortions of non-constant modulus modulated signals.
Proceedings ArticleDOI
Fully complex backpropagation for constant envelope signal processing
Taehwan Kim,Tulay Adali +1 more
TL;DR: A feedforward neural network architecture employing hyperbolic tangent tanh(z) function defined in the entire complex domain, which can easily outperform the non-analytic split complex activation function in convergence speed and achievable minimum squared error when the domain is bounded around the unit circle.