10 papers
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…
Component Centric Placement Using Deep Reinforcement Learning
Kart Leong Lim
Automated placement of components on printed circuit boards (PCBs) is a critical stage in placement layout design. While reinforcement learning (RL) has been successfully applied t…
Inverse prediction of capacitor multiphysics dynamic parameters using deep generative model
Kart-Leong Lim, Rahul Dutta, Mihai Rotaru
Finite element simulations are run by package design engineers to model design structures. The process is irreversible meaning every minute structural adjustment requires a fresh i…
Physics Informed Neural Network using Finite Difference Method
Kart Leong Lim, Rahul Dutta, Mihai Rotaru
In recent engineering applications using deep learning, physics-informed neural network (PINN) is a new development as it can exploit the underlying physics of engineering systems.…
Prognostics and Health Management of Wafer Chemical-Mechanical Polishing System using Autoencoder
Kart-Leong Lim, Rahul Dutta
The Prognostics and Health Management Data Challenge (PHM) 2016 tracks the health state of components of a semiconductor wafer polishing process. The ultimate goal is to develop an…
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,…
Deep clustering using adversarial net based clustering loss
Kart-Leong Lim
Deep clustering is a recent deep learning technique which combines deep learning with traditional unsupervised clustering. At the heart of deep clustering is a loss function which…
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…