arXiv subjects

Hwee Kuan Lee

Publications and source records attributed to Hwee Kuan Lee.

At least 37 records · Page 2Linked to original sources

arXiv2020

Machine-Learning Study using Improved Correlation Configuration and Application to Quantum Monte Carlo Simulation

We use the Fortuin-Kasteleyn representation based improved estimator of the correlation configuration as an alternative to the ordinary correlation configuration in the machine-learning study of the phase classification of spin models. The phases of classical spin models are classified using the improved estimators, and the method is also applied to the quantum Monte Carlo simulation using the loop algorithm. We analyze the Berezinskii-Kosterlitz-Thouless (BKT) transition of the spin 1/2 quantum XY model on the square lattice. We classify the BKT phase and the paramagnetic phase of the quantum XY model using the machine-learning approach. We show that the classification of the quantum XY model can be performed by using the training data of the classical XY model.

cond-mat.stat-mech↗

arXiv2020

Studying The Effect of MIL Pooling Filters on MIL Tasks

There are different multiple instance learning (MIL) pooling filters used in MIL models. In this paper, we study the effect of different MIL pooling filters on the performance of MIL models in real world MIL tasks. We designed a neural network based MIL framework with 5 different MIL pooling filters: `max', `mean', `attention', `distribution' and `distribution with attention'. We also formulated 5 different MIL tasks on a real world lymph node metastases dataset. We found that the performance of our framework in a task is different for different filters. We also observed that the performances of the five pooling filters are also different from task to task. Hence, the selection of a correct MIL pooling filter for each MIL task is crucial for better performance. Furthermore, we noticed that models with `distribution' and `distribution with attention' pooling filters consistently perform well in almost all of the tasks. We attribute this phenomena to the amount of information captured by `distribution' based pooling filters. While point estimate based pooling filters, like `max' and `mean', produce point estimates of distributions, `distribution' based pooling filters capture the full information in distributions. Lastly, we compared the performance of our neural network model with `distribution' pooling filter with the performance of the best MIL methods in the literature on classical MIL datasets and our model outperformed the others.

cs.CV↗

arXiv2020

Regional Registration of Whole Slide Image Stacks Containing Highly Deformed Artefacts

Motivation: High resolution 2D whole slide imaging provides rich information about the tissue structure. This information can be a lot richer if these 2D images can be stacked into a 3D tissue volume. A 3D analysis, however, requires accurate reconstruction of the tissue volume from the 2D image stack. This task is not trivial due to the distortions that each individual tissue slice experiences while cutting and mounting the tissue on the glass slide. Performing registration for the whole tissue slices may be adversely affected by the deformed tissue regions. Consequently, regional registration is found to be more effective. In this paper, we propose an accurate and robust regional registration algorithm for whole slide images which incrementally focuses registration on the area around the region of interest. Results: Using mean similarity index as the metric, the proposed algorithm (mean $\pm$ std: $0.84 \pm 0.11$) followed by a fine registration algorithm ($0.86 \pm 0.08$) outperformed the state-of-the-art linear whole tissue registration algorithm ($0.74 \pm 0.19$) and the regional version of this algorithm ($0.81 \pm 0.15$). The proposed algorithm also outperforms the state-of-the-art nonlinear registration algorithm (original : $0.82 \pm 0.12$, regional : $0.77 \pm 0.22$) for whole slide images and a recently proposed patch-based registration algorithm (patch size 256: $0.79 \pm 0.16$ , patch size 512: $0.77 \pm 0.16$) for medical images. Availability: The C++ implementation code is available online at the github repository: https://github.com/MahsaPaknezhad/WSIRegistration

eess.IV↗

arXiv2020

Enhancing Transformation-based Defenses using a Distribution Classifier

Adversarial attacks on convolutional neural networks (CNN) have gained significant attention and there have been active research efforts on defense mechanisms. Stochastic input transformation methods have been proposed, where the idea is to recover the image from adversarial attack by random transformation, and to take the majority vote as consensus among the random samples. However, the transformation improves the accuracy on adversarial images at the expense of the accuracy on clean images. While it is intuitive that the accuracy on clean images would deteriorate, the exact mechanism in which how this occurs is unclear. In this paper, we study the distribution of softmax induced by stochastic transformations. We observe that with random transformations on the clean images, although the mass of the softmax distribution could shift to the wrong class, the resulting distribution of softmax could be used to correct the prediction. Furthermore, on the adversarial counterparts, with the image transformation, the resulting shapes of the distribution of softmax are similar to the distributions from the clean images. With these observations, we propose a method to improve existing transformation-based defenses. We train a separate lightweight distribution classifier to recognize distinct features in the distributions of softmax outputs of transformed images. Our empirical studies show that our distribution classifier, by training on distributions obtained from clean images only, outperforms majority voting for both clean and adversarial images. Our method is generic and can be integrated with existing transformation-based defenses.

cs.LG↗

arXiv2020

Weakly Supervised Clustering by Exploiting Unique Class Count

A weakly supervised learning based clustering framework is proposed in this paper. As the core of this framework, we introduce a novel multiple instance learning task based on a bag level label called unique class count ($ucc$), which is the number of unique classes among all instances inside the bag. In this task, no annotations on individual instances inside the bag are needed during training of the models. We mathematically prove that with a perfect $ucc$ classifier, perfect clustering of individual instances inside the bags is possible even when no annotations on individual instances are given during training. We have constructed a neural network based $ucc$ classifier and experimentally shown that the clustering performance of our framework with our weakly supervised $ucc$ classifier is comparable to that of fully supervised learning models where labels for all instances are known. Furthermore, we have tested the applicability of our framework to a real world task of semantic segmentation of breast cancer metastases in histological lymph node sections and shown that the performance of our weakly supervised framework is comparable to the performance of a fully supervised Unet model.

cs.CV↗

arXiv2020

Machine-Learning Studies on Spin Models

With the recent developments in machine learning, Carrasquilla and Melko have proposed a paradigm that is complementary to the conventional approach for the study of spin models. As an alternative to investigating the thermal average of macroscopic physical quantities, they have used the spin configurations for the classification of the disordered and ordered phases of a phase transition through machine learning. We extend and generalize this method. We focus on the configuration of the long-range correlation function instead of the spin configuration itself, which enables us to provide the same treatment to multi-component systems and the systems with a vector order parameter. We analyze the Berezinskii-Kosterlitz-Thouless (BKT) transition with the same technique to classify three phases: the disordered, the BKT, and the ordered phases. We also present the classification of a model using the training data of a different model.

cond-mat.stat-mech↗

arXiv2019

Gated-Dilated Networks for Lung Nodule Classification in CT scans

Different types of Convolutional Neural Networks (CNNs) have been applied to detect cancerous lung nodules from computed tomography (CT) scans. However, the size of a nodule is very diverse and can range anywhere between 3 and 30 millimeters. The high variation of nodule sizes makes classifying them a difficult and challenging task. In this study, we propose a novel CNN architecture called Gated-Dilated (GD) networks to classify nodules as malignant or benign. Unlike previous studies, the GD network uses multiple dilated convolutions instead of max-poolings to capture the scale variations. Moreover, the GD network has a Context-Aware sub-network that analyzes the input features and guides the features to a suitable dilated convolution. We evaluated the proposed network on more than 1,000 CT scans from the LIDC-LDRI dataset. Our proposed network outperforms state-of-the-art baseline models including Multi-Crop, Resnet, and Densenet, with an AUC of >0.95. Compared to the baseline models, the GD network improves the classification accuracies of mid-range sized nodules. Furthermore, we observe a relationship between the size of the nodule and the attention signal generated by the Context-Aware sub-network, which validates our new network architecture.

cs.CV↗

arXiv2019

Cribriform pattern detection in prostate histopathological images using deep learning models

Architecture, size, and shape of glands are most important patterns used by pathologists for assessment of cancer malignancy in prostate histopathological tissue slides. Varying structures of glands along with cumbersome manual observations may result in subjective and inconsistent assessment. Cribriform gland with irregular border is an important feature in Gleason pattern 4. We propose using deep neural networks for cribriform pattern classification in prostate histopathological images. $163708$ Hematoxylin and Eosin (H\&E) stained images were extracted from histopathologic tissue slides of $19$ patients with prostate cancer and annotated for cribriform patterns. Our automated image classification system analyses the H\&E images to classify them as either `Cribriform' or `Non-cribriform'. Our system uses various deep learning approaches and hand-crafted image pixel intensity-based features. We present our results for cribriform pattern detection across various parameters and configuration allowed by our system. The combination of fine-tuned deep learning models outperformed the state-of-art nuclei feature based methods. Our image classification system achieved the testing accuracy of $85.93~\pm~7.54$ (cross-validated) and $88.04~\pm~5.63$ ( additional unseen test set) across three folds. In this paper, we present an annotated cribriform dataset along with analysis of deep learning models and hand-crafted features for cribriform pattern detection in prostate histopathological images.

eess.IV↗

arXiv2019

Theoretical and Experimental Analysis on the Generalizability of Distribution Regression Network

There is emerging interest in performing regression between distributions. In contrast to prediction on single instances, these machine learning methods can be useful for population-based studies or on problems that are inherently statistical in nature. The recently proposed distribution regression network (DRN) has shown superior performance for the distribution-to-distribution regression task compared to conventional neural networks. However, in Kou et al. (2018) and some other works on distribution regression, there is a lack of comprehensive comparative study on both theoretical basis and generalization abilities of the methods. We derive some mathematical properties of DRN and qualitatively compare it to conventional neural networks. We also perform comprehensive experiments to study the generalizability of distribution regression models, by studying their robustness to limited training data, data sampling noise and task difficulty. DRN consistently outperforms conventional neural networks, requiring fewer training data and maintaining robust performance with noise. Furthermore, the theoretical properties of DRN can be used to provide some explanation on the ability of DRN to achieve better generalization performance than conventional neural networks.

cs.LG↗

arXiv2019

Fence GAN: Towards Better Anomaly Detection

Anomaly detection is a classical problem where the aim is to detect anomalous data that do not belong to the normal data distribution. Current state-of-the-art methods for anomaly detection on complex high-dimensional data are based on the generative adversarial network (GAN). However, the traditional GAN loss is not directly aligned with the anomaly detection objective: it encourages the distribution of the generated samples to overlap with the real data and so the resulting discriminator has been found to be ineffective as an anomaly detector. In this paper, we propose simple modifications to the GAN loss such that the generated samples lie at the boundary of the real data distribution. With our modified GAN loss, our anomaly detection method, called Fence GAN (FGAN), directly uses the discriminator score as an anomaly threshold. Our experimental results using the MNIST, CIFAR10 and KDD99 datasets show that Fence GAN yields the best anomaly classification accuracy compared to state-of-the-art methods.

cs.LG↗

arXiv2018

A Compact Network Learning Model for Distribution Regression

Despite the superior performance of deep learning in many applications, challenges remain in the area of regression on function spaces. In particular, neural networks are unable to encode function inputs compactly as each node encodes just a real value. We propose a novel idea to address this shortcoming: to encode an entire function in a single network node. To that end, we design a compact network representation that encodes and propagates functions in single nodes for the distribution regression task. Our proposed Distribution Regression Network (DRN) achieves higher prediction accuracies while being much more compact and uses fewer parameters than traditional neural networks.

cs.LG↗

arXiv2018

Flipped-Adversarial AutoEncoders

We propose a flipped-Adversarial AutoEncoder (FAAE) that simultaneously trains a generative model G that maps an arbitrary latent code distribution to a data distribution and an encoder E that embodies an "inverse mapping" that encodes a data sample into a latent code vector. Unlike previous hybrid approaches that leverage adversarial training criterion in constructing autoencoders, FAAE minimizes re-encoding errors in the latent space and exploits adversarial criterion in the data space. Experimental evaluations demonstrate that the proposed framework produces sharper reconstructed images while at the same time enabling inference that captures rich semantic representation of data.

cs.LG↗

arXiv2015

Dynamical traps in Wang-Landau sampling of continuous systems: Mechanism and solution

We study the mechanism behind dynamical trappings experienced during Wang-Landau sampling of continuous systems reported by several authors. Trapping is caused by the random walker coming close to a local energy extremum, although the mechanism is different from that of critical slowing down encountered in conventional molecular dynamics or Monte Carlo simulations. When trapped, the random walker misses entire or even several stages of Wang-Landau modification factor reduction, leading to inadequate sampling of configuration space and a rough density-of-states even though the modification factor has been reduced to very small values. Trapping is dependent on specific systems, the choice of energy bins, and Monte Carlo step size, making it highly unpredictable. A general, simple, and effective solution is proposed where the configurations of multiple parallel Wang-Landau trajectories are inter-swapped to prevent trapping. We also explain why swapping frees the random walker from such traps. The efficacy of the proposed algorithm is demonstrated.

cond-mat.stat-mech↗

arXiv2013

Dynamically Optimized Wang-Landau Sampling with Adaptive Trial Moves and Modification Factors

The density of states of continuous models is known to span many orders of magnitudes at different energies due to the small volume of phase space near the ground state. Consequently, the traditional Wang-Landau sampling which uses the same trial move for all energies faces difficulties sampling the low entropic states. We developed an adaptive variant of the Wang-Landau algorithm that very effectively samples the density of states of continuous models across the entire energy range. By extending the acceptance ratio method of Bouzida, Kumar, and Swendsen such that the step size of the trial move and acceptance rate are adapted in an energy-dependent fashion, the random walker efficiently adapts its sampling according to the local phase space structure. The Wang-Landau modification factor is also made energy-dependent in accordance with the step size, enhancing the accumulation of the density of states. Numerical simulations show that our proposed method performs much better than the traditional Wang-Landau sampling.

cond-mat.stat-mech↗

arXiv2011

A Finite State Model for Time Travel

A time machine that sends information back to the past may, in principle, be built using closed time-like curves. However, the realization of a time machine must be congruent with apparent paradoxes that arise from traveling back in time. Using a simple model to analyze the consequences of time travel, we show that several paradoxes, including the grandfather paradox and Deutsch's unproven theorem paradox, are precluded by basic axioms of probability. However, our model does not prohibit traveling back in time to affect past events in a self-consistent manner.

gr-qc↗

arXiv2008

Pseudo spin-orbit coupling of Dirac particles in graphene spintronics

We study the pseudo spin-orbital (SO) effects experienced by massive Dirac particles in graphene, which can potentially be of a larger magnitude compared to the conventional Rashba SO effects experienced by particles in a 2DEG semiconductor heterostructure. In order to generate a uniform vertical pseudo SO field, we propose an artificial atomic structure, consisting of a graphene ring and a charged nanodot at the center which produces a large radial electric field. In this structure, a large pseudo SO coupling strength can be achieved by accelerating the Dirac particles around the ring, due to the small energy gap in graphene and the large radial electric field emanating from the charged nanodot. We discuss the theoretical possibility of harnessing the pseudo SO effects in mesoscopic applications, e.g. pseudo spin relaxation and switching.

cond-mat.mes-hall↗

arXiv2007

Analytical Solution to Transport in Brownian Ratchets via Gambler's Ruin Model

We present an analogy between the classic Gambler's Ruin problem and the thermally-activated dynamics in periodic Brownian ratchets. By considering each periodic unit of the ratchet as a site chain, we calculated the transition probabilities and mean first passage time for transitions between energy minima of adjacent units. We consider the specific case of Brownian ratchets driven by Markov dichotomous noise. The explicit solution for the current is derived for any arbitrary temperature, and is verified numerically by Langevin simulations. The conditions for vanishing current and current reversal in the ratchet are obtained and discussed.

cond-mat.stat-mech↗

arXiv2006

Time Quantified Monte Carlo Algorithm for Interacting Spin Array Micromagnetic Dynamics

In this paper, we reexamine the validity of using time quantified Monte Carlo (TQMC) method [Phys. Rev. Lett. 84, 163 (2000); Phys. Rev. Lett. 96, 067208 (2006)] in simulating the stochastic dynamics of interacting magnetic nanoparticles. The Fokker-Planck coefficients corresponding to both TQMC and Langevin dynamical equation (Landau-Lifshitz-Gilbert, LLG) are derived and compared in the presence of interparticle interactions. The time quantification factor is obtained and justified. Numerical verification is shown by using TQMC and Langevin methods in analyzing spin-wave dispersion in a linear array of magnetic nanoparticles.

cond-mat.stat-mech↗