arXiv subjects

Phuoc Nguyen

Publications and source records attributed to Phuoc Nguyen.

24 records · Page 2Linked to original sources

arXiv2018

Hybrid Generative-Discriminative Models for Inverse Materials Design

Discovering new physical products and processes often demands enormous experimentation and expensive simulation. To design a new product with certain target characteristics, an extensive search is performed in the design space by trying out a large number of design combinations before reaching to the target characteristics. However, forward searching for the target design becomes prohibitive when the target is itself moving or only partially understood. To address this bottleneck, we propose to use backward prediction by leveraging the rich data generated during earlier exploration and construct a machine learning framework to predict the design parameters for any target in a single step. This poses two technical challenges: the first caused due to one-to-many mapping when learning the inverse problem and the second caused due to an user specifying the target specifications only partially. To overcome the challenges, we formulate this problem as conditional density estimation under high-dimensional setting with incomplete input and multimodal output. We solve the problem through a deep hybrid generative-discriminative model, which is trained end-to-end to predict the optimum design.

stat.ML↗

arXiv2018

Resset: A Recurrent Model for Sequence of Sets with Applications to Electronic Medical Records

Modern healthcare is ripe for disruption by AI. A game changer would be automatic understanding the latent processes from electronic medical records, which are being collected for billions of people worldwide. However, these healthcare processes are complicated by the interaction between at least three dynamic components: the illness which involves multiple diseases, the care which involves multiple treatments, and the recording practice which is biased and erroneous. Existing methods are inadequate in capturing the dynamic structure of care. We propose Resset, an end-to-end recurrent model that reads medical record and predicts future risk. The model adopts the algebraic view in that discrete medical objects are embedded into continuous vectors lying in the same space. We formulate the problem as modeling sequences of sets, a novel setting that have rarely, if not, been addressed. Within Resset, the bag of diseases recorded at each clinic visit is modeled as function of sets. The same hold for the bag of treatments. The interaction between the disease bag and the treatment bag at a visit is modeled in several, one of which as residual of diseases minus the treatments. Finally, the health trajectory, which is a sequence of visits, is modeled using a recurrent neural network. We report results on over a hundred thousand hospital visits by patients suffered from two costly chronic diseases -- diabetes and mental health. Resset shows promises in multiple predictive tasks such as readmission prediction, treatments recommendation and diseases progression.

cs.NE↗

arXiv2018

Intelligent Device Discovery in the Internet of Things - Enabling the Robot Society

The Internet of Things (IoT) is continuously growing to connect billions of smart devices anywhere and anytime in an Internet-like structure, which enables a variety of applications, services and interactions between human and objects. In the future, the smart devices are supposed to be able to autonomously discover a target device with desired features and generate a set of entirely new services and applications that are not supervised or even imagined by human beings. The pervasiveness of smart devices, as well as the heterogeneity of their design and functionalities, raise a major concern: How can a smart device efficiently discover a desired target device? In this paper, we propose a Social-Aware and Distributed (SAND) scheme that achieves a fast, scalable and efficient device discovery in the IoT. The proposed SAND scheme adopts a novel device ranking criteria that measures the device's degree, social relationship diversity, clustering coefficient and betweenness. Based on the device ranking criteria, the discovery request can be guided to travel through critical devices that stand at the major intersections of the network, and thus quickly reach the desired target device by contacting only a limited number of intermediate devices. With the help of such an intelligent device discovery as SAND, the IoT devices, as well as other computing facilities, software and data on the Internet, can autonomously establish new social connections with each other as human being do. They can formulate self-organized computing groups to perform required computing tasks, facilitate a fusion of a variety of computing service, network service and data to generate novel applications and services, evolve from the individual aritificial intelligence to the collaborative intelligence, and eventually enable the birth of a robot society.

cs.AI↗

arXiv2017

Finding Algebraic Structure of Care in Time: A Deep Learning Approach

Understanding the latent processes from Electronic Medical Records could be a game changer in modern healthcare. However, the processes are complex due to the interaction between at least three dynamic components: the illness, the care and the recording practice. Existing methods are inadequate in capturing the dynamic structure of care. We propose an end-to-end model that reads medical record and predicts future risk. The model adopts the algebraic view in that discrete medical objects are embedded into continuous vectors lying in the same space. The bag of disease and comorbidities recorded at each hospital visit are modeled as function of sets. The same holds for the bag of treatments. The interaction between diseases and treatments at a visit is modeled as the residual of the diseases minus the treatments. Finally, the health trajectory, which is a sequence of visits, is modeled using a recurrent neural network. We report preliminary results on chronic diseases - diabetes and mental health - for predicting unplanned readmission.

cs.LG↗

arXiv2017

Deep Learning to Attend to Risk in ICU

Modeling physiological time-series in ICU is of high clinical importance. However, data collected within ICU are irregular in time and often contain missing measurements. Since absence of a measure would signify its lack of importance, the missingness is indeed informative and might reflect the decision making by the clinician. Here we propose a deep learning architecture that can effectively handle these challenges for predicting ICU mortality outcomes. The model is based on Long Short-Term Memory, and has layered attention mechanisms. At the sensing layer, the model decides whether to observe and incorporate parts of the current measurements. At the reasoning layer, evidences across time steps are weighted and combined. The model is evaluated on the PhysioNet 2012 dataset showing competitive and interpretable results.

cs.LG↗

arXiv2016

Deepr: A Convolutional Net for Medical Records

Feature engineering remains a major bottleneck when creating predictive systems from electronic medical records. At present, an important missing element is detecting predictive regular clinical motifs from irregular episodic records. We present Deepr (short for Deep record), a new end-to-end deep learning system that learns to extract features from medical records and predicts future risk automatically. Deepr transforms a record into a sequence of discrete elements separated by coded time gaps and hospital transfers. On top of the sequence is a convolutional neural net that detects and combines predictive local clinical motifs to stratify the risk. Deepr permits transparent inspection and visualization of its inner working. We validate Deepr on hospital data to predict unplanned readmission after discharge. Deepr achieves superior accuracy compared to traditional techniques, detects meaningful clinical motifs, and uncovers the underlying structure of the disease and intervention space.

stat.ML↗