5 papers · 1 filter
Recursive transformers for semiconductor thermo-mechanical reliability
Kart-leong Lim
Transformer-based surrogate models are increasingly used to replace expensive first-principles simulation in engineering design. But conventional transformer architectures are ofte…
PYPM-GGD: Pitman-Yor Process Mixture with Generalized Gaussian Density using ADAM
Kart-Leong Lim
Large scale Bayesian nonparametrics (BNP) learner such as Stochastic Variational Inference (SVI) can handle datasets with large class number and large training size at fractional c…
Deep Clustering using Dirichlet Process Gaussian Mixture and Alpha Jensen-Shannon Divergence Clustering Loss
Kart-Leong Lim
Deep clustering is an emerging topic in deep learning where traditional clustering is performed in deep learning feature space. However, clustering and deep learning are often mutu…
Fisher Information based Stochastic Gradient Ascent for Online Learning of Dirichlet Process Mixture and Theory
Kart-Leong Lim, Xudong Jiang
Scalable algorithms of posterior approximation allow Bayesian nonparametrics such as Dirichlet process mixture to scale up to larger dataset at fractional cost. Recent algorithms,…
Boundary-Decoder network for inverse prediction of capacitor electrostatic analysis
Kart-Leong Lim, Rahul Dutta, Mihai Rotaru
Traditional electrostatic simulation are meshed-based methods which convert partial differential equations into an algebraic system of equations and their solutions are approximate…