Lei Chen

Bio: Lei Chen is an academic researcher from University of Michigan. The author has contributed to research in topics: Finite element method & Materials science. The author has an hindex of 31, co-authored 139 publications receiving 8114 citations. Previous affiliations of Lei Chen include Nanjing Tech University & University of Alberta.

Universal approximation using incremental constructive feedforward networks with random hidden nodes

Abstract: According to conventional neural network theories, single-hidden-layer feedforward networks (SLFNs) with additive or radial basis function (RBF) hidden nodes are universal approximators when all the parameters of the networks are allowed adjustable. However, as observed in most neural network implementations, tuning all the parameters of the networks may cause learning complicated and inefficient, and it may be difficult to train networks with nondifferential activation functions such as threshold networks. Unlike conventional neural network theories, this paper proves in an incremental constructive method that in order to let SLFNs work as universal approximators, one may simply randomly choose hidden nodes and then only need to adjust the output weights linking the hidden layer and the output layer. In such SLFNs implementations, the activation functions for additive nodes can be any bounded nonconstant piecewise continuous functions g:R→R and the activation functions for RBF nodes can be any integrable piecewise continuous functions g:R→R and ∫Rg(x)dx≠0. The proposed incremental method is efficient not only for SFLNs with continuous (including nondifferentiable) activation functions but also for SLFNs with piecewise continuous (such as threshold) activation functions. Compared to other popular methods such a new network is fully automatic and users need not intervene the learning process by manually tuning control parameters.

Flexible high-temperature dielectric materials from polymer nanocomposites

Abstract: Dielectric materials, which store energy electrostatically, are ubiquitous in advanced electronics and electric power systems. Compared to their ceramic counterparts, polymer dielectrics have higher breakdown strengths and greater reliability, are scalable, lightweight and can be shaped into intricate configurations, and are therefore an ideal choice for many power electronics, power conditioning, and pulsed power applications. However, polymer dielectrics are limited to relatively low working temperatures, and thus fail to meet the rising demand for electricity under the extreme conditions present in applications such as hybrid and electric vehicles, aerospace power electronics, and underground oil and gas exploration. Here we describe crosslinked polymer nanocomposites that contain boron nitride nanosheets, the dielectric properties of which are stable over a broad temperature and frequency range. The nanocomposites have outstanding high-voltage capacitive energy storage capabilities at record temperatures (a Weibull breakdown strength of 403 megavolts per metre and a discharged energy density of 1.8 joules per cubic centimetre at 250 degrees Celsius). Their electrical conduction is several orders of magnitude lower than that of existing polymers and their high operating temperatures are attributed to greatly improved thermal conductivity, owing to the presence of the boron nitride nanosheets, which improve heat dissipation compared to pristine polymers (which are inherently susceptible to thermal runaway). Moreover, the polymer nanocomposites are lightweight, photopatternable and mechanically flexible, and have been demonstrated to preserve excellent dielectric and capacitive performance after intensive bending cycles. These findings enable broader applications of organic materials in high-temperature electronics and energy storage devices.

Ferroelectricity of CH3NH3PbI3 Perovskite

Abstract: Ferroelectricity has been believed to be an important but controversial origin of the excellent photovoltaic performance of organometal trihalide perovskites (OTPs). Here we investigate the ferroelectricity of a prototype OTP, CH3NH3PbI3 (MAPbI3), both theoretically and experimentally. Our first-principles calculations based on 3-D periodic boundary conditions reveal that a ferroelectric structure with polarization of ∼8 μC/cm2 is the globally stable one among all possible tetragonal structures; however, experimentally no room-temperature ferroelectricity is observed by using polarization–electric field hysteresis measurements and piezoresponse force microscopy. The discrepancy between our theoretical and experimental results is attributed to the dynamic orientational disorder of MA+ groups and the semiconducting nature of MAPbI3 at room temperature. Therefore, we conclude that MAPbI3 is not ferroelectric at room temperature; however, it is possible to induce and experimentally observe apparent ferroelect...

The Graph Neural Network Model

Abstract: Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains. This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, and undirected, implements a function tau(G,n) isin IRm that maps a graph G and one of its nodes n into an m-dimensional Euclidean space. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities.

Extreme Learning Machine for Regression and Multiclass Classification

Abstract: Due to the simplicity of their implementations, least square support vector machine (LS-SVM) and proximal support vector machine (PSVM) have been widely used in binary classification applications. The conventional LS-SVM and PSVM cannot be used in regression and multiclass classification applications directly, although variants of LS-SVM and PSVM have been proposed to handle such cases. This paper shows that both LS-SVM and PSVM can be simplified further and a unified learning framework of LS-SVM, PSVM, and other regularization algorithms referred to extreme learning machine (ELM) can be built. ELM works for the “generalized” single-hidden-layer feedforward networks (SLFNs), but the hidden layer (or called feature mapping) in ELM need not be tuned. Such SLFNs include but are not limited to SVM, polynomial network, and the conventional feedforward neural networks. This paper shows the following: 1) ELM provides a unified learning platform with a widespread type of feature mappings and can be applied in regression and multiclass classification applications directly; 2) from the optimization method point of view, ELM has milder optimization constraints compared to LS-SVM and PSVM; 3) in theory, compared to ELM, LS-SVM and PSVM achieve suboptimal solutions and require higher computational complexity; and 4) in theory, ELM can approximate any target continuous function and classify any disjoint regions. As verified by the simulation results, ELM tends to have better scalability and achieve similar (for regression and binary class cases) or much better (for multiclass cases) generalization performance at much faster learning speed (up to thousands times) than traditional SVM and LS-SVM.

Toward Safe Lithium Metal Anode in Rechargeable Batteries: A Review.

Abstract: The lithium metal battery is strongly considered to be one of the most promising candidates for high-energy-density energy storage devices in our modern and technology-based society. However, uncontrollable lithium dendrite growth induces poor cycling efficiency and severe safety concerns, dragging lithium metal batteries out of practical applications. This review presents a comprehensive overview of the lithium metal anode and its dendritic lithium growth. First, the working principles and technical challenges of a lithium metal anode are underscored. Specific attention is paid to the mechanistic understandings and quantitative models for solid electrolyte interphase (SEI) formation, lithium dendrite nucleation, and growth. On the basis of previous theoretical understanding and analysis, recently proposed strategies to suppress dendrite growth of lithium metal anode and some other metal anodes are reviewed. A section dedicated to the potential of full-cell lithium metal batteries for practical applicatio...

Ionic transport in hybrid lead iodide perovskite solar cells

Abstract: Understanding the mechanism of ionic transport in organic–inorganic halide perovskites is crucial for the design of future solar cells. Here, Eames et al. undertake a combined experimental and computational study to elucidate the ion conducting species and help rationalize the unusual behaviour observed in these perovskite-based devices.