Stephen Wu

Stephen Wu

Auto-generated profile, based on publicly available information

Stephen Wu

The Institute of Statistical Mathematics Research Organization of Information and Systems Tokyo Japan

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 June 2019 in npj Computational Materials
Verified
Journal Article
Open access
PDF file
SWStephen Wu
Stephen Wu
YKYukiko Kondo
Yukiko Kondo
MKMasa-Aki Kakimoto
Masa-Aki Kakimoto
BYBin Yang
Bin Yang
HYHironao Yamada
Hironao Yamada
RYRyo Yoshida
Ryo Yoshida
The use of machine learning in computational molecular design has great potential to accelerate the discovery of innovative materials. However, its practical benefits still remain unproven in real-world applications, particularly in polymer science. We demonstrate the successful discovery of new polymers with high thermal conductivity, inspired by machine-learning-assisted polymer chemistry. This discovery was made by the interplay between machine intelligence trained on a substantially limited amount of polymeric properties data, expertise from laboratory synthesis and advanced technologies for thermophysical property measurements. Using a molecular design algorithm trained to recognize quantitative structure—property relationships with respect to thermal conductivity and other targeted polymeric properties, we identified thousands of promising hypothetical polymers. From these candidates, three were selected for monomer synthesis and polymerization because of their synthetic accessibility and their potential for ease of processing in further applications. The synthesized polymers reached thermal conductivities of 0.18–0.41 W/mK, which are comparable to those of state-of-the-art polymers in non-composite thermo-plastics.

30 September 2019 in ACS Central Science
Verified
Journal Article
Open access
HYHironao Yamada
Hironao Yamada
CLChang Liu
Chang Liu
SWStephen Wu
Stephen Wu
YKYukinori Koyama
Yukinori Koyama
SJShenghong Ju
Shenghong Ju
RYRyo Yoshida
Ryo Yoshida
There is a growing demand for the use of machine learning (ML) to derive fast-to-evaluate surrogate models of materials properties. In recent years, a broad array of materials property databases have emerged as part of a digital transformation of materials science. However, recent technological advances in ML are not fully exploited because of the insufficient volume and diversity of materials data. An ML framework called “transfer learning” has considerable potential to overcome the problem of limited amounts of materials data. Transfer learning relies on the concept that various property types, such as physical, chemical, electronic, thermodynamic, and mechanical properties, are physically interrelated. For a given target property to be predicted from a limited supply of training data, models of related proxy properties are pretrained using sufficient data; these models capture common features relevant to the target task. Repurposing of such machine-acquired features on the target task yields outstanding prediction performance even with exceedingly small data sets, as if highly experienced human experts can make rational inferences even for considerably less experienced tasks. In this study, to facilitate widespread use of transfer learning, we develop a pretrained model library called XenonPy.MDL. In this first release, the library comprises more than 140 000 pretrained models for various properties of small molecules, polymers, and inorganic crystalline materials. Along with these pretrained models, we describe some outstanding successes of transfer learning in different scenarios such as building models with only dozens of materials data, increasing the ability of extrapolative prediction through a strategic model transfer, and so on. Remarkably, transfer learning has autonomously identified rather nontrivial transferability across different properties transcending the different disciplines of materials science; for example, our analysis has revealed underlying bridges between small molecules and polymers and between organic and inorganic chemistry.

1 March 2014 in Computer-Aided Civil and Infrastructure Engineering
Verified
Journal Article
Open access
PDF file
YHYong Huang
Yong Huang
JBJames L. Beck
James L. Beck
SWStephen Wu
Stephen Wu
HLHui Li
Hui Li
In structural health monitoring (SHM) systems for civil structures, massive amounts of data are often generated that need data compression techniques to reduce the cost of signal transfer and storage, meanwhile offering a simple sensing system. Compressive sensing (CS) is a novel data acquisition method whereby the compression is done in a sensor simultaneously with the sampling. If the original sensed signal is sufficiently sparse in terms of some orthogonal basis (e.g., a sufficient number of wavelet coefficients are zero or negligibly small), the decompression can be done essentially perfectly up to some critical compression ratio; otherwise there is a trade-off between the reconstruction error and how much compression occurs. In this article, a Bayesian compressive sensing (BCS) method is investigated that uses sparse Bayesian learning to reconstruct signals from a compressive sensor. By explicitly quantifying the uncertainty in the reconstructed signal from compressed data, the BCS technique exhibits an obvious benefit over existing regularized norm-minimization CS methods that provide a single signal estimate. However, current BCS algorithms suffer from a robustness problem: sometimes the reconstruction errors are very large when the number of measurements K are a lot less than the number of signal degrees of freedom N that are needed to capture the signal accurately in a directly sampled form. In this article, we present improvements to the BCS reconstruction method to enhance its robustness so that even higher compression ratios N/K can be used and we examine the trade-off between efficiently compressing data and accurately decompressing it. Synthetic data and actual acceleration data collected from a bridge SHM system are used as examples. Compared with the state-of-the-art BCS reconstruction algorithms, the improved BCS algorithm demonstrates superior performance. With the same acceptable error rate based on a specified threshold of reconstruction error, the proposed BCS algorithm works with relatively large compression ratios and it can achieve perfect lossless compression performance with quite high compression ratios. Furthermore, the error bars for the signal reconstruction are also quantified effectively. ? 2013 Computer-Aided Civil and Infrastructure Engineering.

18 August 2020 in npj Computational Materials
Verified
Journal Article
Open access
PDF file
BMBoyuan Ma
Boyuan Ma
XWXiaoyan Wei
Xiaoyan Wei
CLChuni Liu
Chuni Liu
Xiaojuan BanXiaojuan Ban
Xiaojuan Ban
Hai-You HuangHai-You Huang
Hai-You Huang
YSYan-Jing Su
Yan-Jing Su
Recent progress in material data mining has been driven by high-capacity models trained on large datasets. However, collecting experimental data (real data) has been extremely costly owing to the amount of human effort and expertise required. Here, we develop a novel transfer learning strategy to address problems of small or insufficient data. This strategy realizes the fusion of real and simulated data and the augmentation of training data in a data mining procedure. For a specific task of grain instance image segmentation, this strategy aims to generate synthetic data by fusing the images obtained from simulating the physical mechanism of grain formation and the “image style” information in real images. The results show that the model trained with the acquired synthetic data and only 35% of the real data can already achieve competitive segmentation performance of a model trained on all of the real data. Because the time required to perform grain simulation and to generate synthetic data are almost negligible as compared to the effort for obtaining real data, our proposed strategy is able to exploit the strong prediction power of deep learning without significantly increasing the experimental burden of training data preparation.

10 July 2023 in Macromolecules
Verified
Journal Article
Open access
YAYuta Aoki
Yuta Aoki
SWStephen Wu
Stephen Wu
TTTeruki Tsurimoto
Teruki Tsurimoto
YHYoshihiro Hayashi
Yoshihiro Hayashi
SMShunya Minami
Shunya Minami
RYRyo Yoshida
Ryo Yoshida

1 April 2015 in Probabilistic Engineering Mechanics
Verified
Journal Article
Closed access
KZKonstantin M. Zuev
Konstantin M. Zuev
SWStephen Wu
Stephen Wu
JBJames L. Beck
James L. Beck