选择性集成学习算法综述

集成学习因其能显著提高一个学习系统的泛化能力而得到了机器学习界的广泛关注,但随着基学习机数目的增多,集成学习机的预测速度明显下降,其所需的存储空间也迅速增加.选择性集成学习的主要目的是进一步改善集成学习机的预测效果,提高集成学习机的预测速度,并降低其存储需求.该文对现有的选择性集成学习算法进行了详细综述,按照算法采用的选择策略对其进行了分类,并分析了各种算法的主要特点,最后对选择性集成学习在将来的可能研究方向进行了探讨.

Application of Fuzzy Automata Theory and Knowledge Based Neural Networks for Development of Basic Learning Model

The paper focuses on amalgamation of automata theory and fuzzy language. It uses adaptive knowledge based abstract framework which uses dynamic neural network framework along with fuzzy automata as Models of Learning, combining the two methodologies the authors develop a new framework termed as Fuzzy Automata based Neural Network （FANN）. It highlights conversion of knowledge rule to fuzzy automata thereby generating a framework FANN. FANN consists of composite fuzzy automation divided into ＂Performance Evaluator＂ and ＂Feature Extraction＂ which takes the help of previously stored samples of similar situations. The authors have extended FANN for Urban Traffic Modeling.

High-throughput studies and machine learning for design of β titanium alloys with optimum properties

Based on experimental data,machine learning(ML) models for Young's modulus,hardness,and hot-working ability of Ti-based alloys were constructed.In the models,the interdiffusion and mechanical property data were high-throughput re-evaluated from composition variations and nanoindentation data of diffusion couples.Then,the Ti-(22±0.5)at.%Nb-(30±0.5)at.%Zr-(4±0.5)at.%Cr(TNZC) alloy with a single body-centered cubic(BCC) phase was screened in an interactive loop.The experimental results exhibited a relatively low Young's modulus of(58±4) GPa,high nanohardness of(3.4±0.2) GPa,high microhardness of HV(520±5),high compressive yield strength of(1220±18) MPa,large plastic strain greater than 30%,and superior dry-and wet-wear resistance.This work demonstrates that ML combined with high-throughput analytic approaches can offer a powerful tool to accelerate the design of multicomponent Ti alloys with desired properties.Moreover,it is indicated that TNZC alloy is an attractive candidate for biomedical applications.

Prediction for Geometric Characteristics of Single Track of Deposition Layer and Surface Roughness in Thin Wire-Based Metal Additive Manufacturing Process

Machine learning prediction models for thin wire-based metal additive manufacturing(MAM)process were proposed,aiming at the complex relationship between the process parameters and the geometric characteristics of single track of the deposition layer and surface roughness.The effects of laser power,wire feeding speed and scanning speed on the width and height of the single track and surface roughness were experimentally studied.The results show that laser power has a significant impact on the width of the single track but little effect on the height.As the wire feeding speed increases,the width and height of the single track increase,especially the height.The faster the scanning speed,the smaller the width of the single track,while the height does not change much.Then,support vector regression(SVR)and artificial neural network(ANN)regression methods were employed to set up prediction models.The SVR and ANN regression models perform well in predicting the width,with a smaller root mean square error and a higher correlation coefficient R2.Compared with the ANN model,the SVR model performs better both in predicting geometric characteristics of single track and surface roughness.Multi-layer thin-walled parts were manufactured to verify the accuracy of the models.

Genomic data mining for functional annotation of human long noncoding RNAs

Life may have begun in an RNA world,which is supported by increasing evidence of the vital role that RNAs perform in biological systems.In the human genome,most genes actually do not encode proteins;they are noncoding RNA genes.The largest class of noncoding genes is known as long noncoding RNAs(lncRNAs),which are transcripts greater in length than 200 nucleotides,but with no protein-coding capacity.While some lncRNAs have been demonstrated to be key regulators of gene expression and 3D genome organization,most lncRNAs are still uncharacterized.We thus propose several data mining and machine learning approaches for the functional annotation of human lncRNAs by leveraging the vast amount of data from genetic and genomic studies.Recent results from our studies and those of other groups indicate that genomic data mining can give insights into lncRNA functions and provide valuable information for experimental studies of candidate lncRNAs associated with human disease.

Problem-Based L2 Learning: Self-Negotiated Linguistic Cognition

The existing literature has revealed that Problem-based Learning （PBL） can improve the cognitive competence of learners, but few studies focus on L2 learning from the perspective of students, or on the relationship between PBL and linguistic cognition. Based on students＇ reflective journals, the researcher＇s observation notes, and interviews with teachers and students, this case study describes the individual and collective self-negotiations during a Problem-Based L2 Learning （PBLL） practice of 157 non-English majors at three universities in Beijing. The current study makes a distinction between surface and deep self-negotiations, and confirms the conception of the self-negotiated L2 cognition of PBLL learners. The research results show （1） that the self-negotiation is a consistent feature of PBLL because the whole PBLL process comprises the cyclic intertwining of individual and collective self-negotiations, （2） that L2 learners manage to achieve individual and collective self-negotiations through cognitive mechanisms of linking, riffling and converging, and （3） that deep self-negotiations in PBLL are more dynamic, interactive, and generative. Pedagogical implications, research limitations, and future directions are also discussed.