Optimization in Machine Learning:a Distribution-Space Approach

We present the viewpoint that optimization problems encountered in machine learning can often be interpreted as minimizing a convex functional over a function space,but with a non-convex constraint set introduced by model parameterization.This observation allows us to repose such problems via a suitable relaxation as convex optimization problems in the space of distributions over the training parameters.We derive some simple relationships between the distribution-space problem and the original problem,e.g.,a distribution-space solution is at least as good as a solution in the original space.Moreover,we develop a numerical algorithm based on mixture distributions to perform approximate optimization directly in the distribution space.Consistency of this approximation is established and the numerical efficacy of the proposed algorithm is illustrated in simple examples.In both theory and practice,this formulation provides an alternative approach to large-scale optimization in machine learning.

A Survey into Teachers＇ Roles in Web-based College English Autonomous Learning

The paper, with the backdrop of web-based autonomous learning put forward by the recent college English teaching reform, aims to explore teachers＇ roles in this learning process in students＇ perception through the means of questionnaires and interviews. It further analyzes the possible reasons why students perceive their teachers＇ roles in such a way, in the hope of providing some implications for web-based college English autonomous learning.

Machine learning algorithms able to predict the prognosis of gastric cancer patients treated with immune checkpoint inhibitors

BACKGROUND Although immune checkpoint inhibitors(ICIs)have demonstrated significant survival benefits in some patients diagnosed with gastric cancer(GC),existing prognostic markers are not universally applicable to all patients with advanced GC.AIM To investigate biomarkers that predict prognosis in GC patients treated with ICIs and develop accurate predictive models.METHODS Data from 273 patients diagnosed with GC and distant metastasis,who un-derwent≥1 cycle(s)of ICIs therapy were included in this study.Patients were randomly divided into training and test sets at a ratio of 7:3.Training set data were used to develop the machine learning models,and the test set was used to validate their predictive ability.Shapley additive explanations were used to provide insights into the best model.RESULTS Among the 273 patients with GC treated with ICIs in this study,112 died within 1 year,and 129 progressed within the same timeframe.Five features related to overall survival and 4 related to progression-free survival were identified and used to construct eXtreme Gradient Boosting(XGBoost),logistic regression,and decision tree.After comprehensive evaluation,XGBoost demonstrated good accuracy in predicting overall survival and progression-free survival.CONCLUSION The XGBoost model aided in identifying patients with GC who were more likely to benefit from ICIs therapy.Patient nutritional status may,to some extent,reflect prognosis.

Convergence analysis for complementary-label learning with kernel ridge regression

Complementary-label learning(CLL)aims at finding a classifier via samples with complementary labels.Such data is considered to contain less information than ordinary-label samples.The transition matrix between the true label and the complementary label,and some loss functions have been developed to handle this problem.In this paper,we show that CLL can be transformed into ordinary classification under some mild conditions,which indicates that the complementary labels can supply enough information in most cases.As an example,an extensive misclassification error analysis was performed for the Kernel Ridge Regression(KRR)method applied to multiple complementary-label learning(MCLL),which demonstrates its superior performance compared to existing approaches.

Recent advances in protein conformation sampling by combining machine learning with molecular simulation

The rapid advancement and broad application of machine learning(ML)have driven a groundbreaking revolution in computational biology.One of the most cutting-edge and important applications of ML is its integration with molecular simulations to improve the sampling efficiency of the vast conformational space of large biomolecules.This review focuses on recent studies that utilize ML-based techniques in the exploration of protein conformational landscape.We first highlight the recent development of ML-aided enhanced sampling methods,including heuristic algorithms and neural networks that are designed to refine the selection of reaction coordinates for the construction of bias potential,or facilitate the exploration of the unsampled region of the energy landscape.Further,we review the development of autoencoder based methods that combine molecular simulations and deep learning to expand the search for protein conformations.Lastly,we discuss the cutting-edge methodologies for the one-shot generation of protein conformations with precise Boltzmann weights.Collectively,this review demonstrates the promising potential of machine learning in revolutionizing our insight into the complex conformational ensembles of proteins.

Incorporation of Learning Strategies into Web-based Autonomous Listening

The thesis introduces a comparative study of students'autonomous listening practice in a web-based autonomous learning center and the traditional teacher-dominated listening practice in a traditional language lab.The purpose of the study is to find how students'listening strategies differ in these two approaches and thereby to find which one better facilitates students'listening proficiency.

Sim-to-Real: A Performance Comparison of PPO, TD3, and SAC Reinforcement Learning Algorithms for Quadruped Walking Gait Generation

The performance of the state-of-the-art Deep Reinforcement algorithms such as Proximal Policy Optimization, Twin Delayed Deep Deterministic Policy Gradient, and Soft Actor-Critic for generating a quadruped walking gait in a virtual environment was presented in previous research work titled “A Comparison of PPO, TD3, and SAC Reinforcement Algorithms for Quadruped Walking Gait Generation”. We demonstrated that the Soft Actor-Critic Reinforcement algorithm had the best performance generating the walking gait for a quadruped in certain instances of sensor configurations in the virtual environment. In this work, we present the performance analysis of the state-of-the-art Deep Reinforcement algorithms above for quadruped walking gait generation in a physical environment. The performance is determined in the physical environment by transfer learning augmented by real-time reinforcement learning for gait generation on a physical quadruped. The performance is analyzed on a quadruped equipped with a range of sensors such as position tracking using a stereo camera, contact sensing of each of the robot legs through force resistive sensors, and proprioceptive information of the robot body and legs using nine inertial measurement units. The performance comparison is presented using the metrics associated with the walking gait: average forward velocity (m/s), average forward velocity variance, average lateral velocity (m/s), average lateral velocity variance, and quaternion root mean square deviation. The strengths and weaknesses of each algorithm for the given task on the physical quadruped are discussed.

A Review of the Effectiveness of Web-based Course with College English Learners' Autonomous Learning

The paper is a literature review, aiming to examine the effectiveness of web-based college English learning which mainly focuses on learners' autonomous learning. Previous studies indicate that the web-based learning can improve learners' autonomous learning, as well as some problems found in their findings. Therefore, this paper first gives a summary and critique of research studies on the web-based autonomous learning and some factors influencing learners' autonomous learning ability;then, areas that deserve further study are also indicated.

Design space exploration of neural network accelerator based on transfer learning

With the increasing demand of computational power in artificial intelligence(AI)algorithms,dedicated accelerators have become a necessity.However,the complexity of hardware architectures,vast design search space,and complex tasks of accelerators have posed significant challenges.Tra-ditional search methods can become prohibitively slow if the search space continues to be expanded.A design space exploration(DSE)method is proposed based on transfer learning,which reduces the time for repeated training and uses multi-task models for different tasks on the same processor.The proposed method accurately predicts the latency and energy consumption associated with neural net-work accelerator design parameters,enabling faster identification of optimal outcomes compared with traditional methods.And compared with other DSE methods by using multilayer perceptron(MLP),the required training time is shorter.Comparative experiments with other methods demonstrate that the proposed method improves the efficiency of DSE without compromising the accuracy of the re-sults.

On Cognitive Style in English Web-based Autonomous Learning

Since Henry Holec first put forward the term‘Autonomy'in 1980's, autonomous learning has been drawing the universal attention of scholars both at home and abroad. Promoting learners' ability of self-regulated learning has been taken as one of the important goals of modern education. College English autonomous learning based on network environment does not mean free study without any restraints or monitoring, but rather involves the self-monitoring and external monitoring. Meanwhile, different learners may have different cognitive styles in their learning processes, which may have an influence on the improvement of the learners' efficiency in the autonomous language learning. Proper monitoring models coordinating with the students' different field cognitive styles.

An Investigation into the Web-Based Learning in Jiangsu Open University(JSOU)——A case Study of College English

College English is a compulsory course for all registered online learners in Jiangsu Open University and students have been practicing web-based learning instead of face-to-face classes ever since 2014.Questionnaires and interviews are adopted to look into the 4-year-long practice of web-based learning in College English in JSOU.By analyzing the data obtained from both teachers and students,the findings show:(1)web-based learning caters to online learners in that the online learning materials,particularly micro-lessons,are well-designed and easily accessible.(2)web-based learning helps teachers monitor the learning process of online learners and therefore assures the quality of online learning.(3)web-based learning enhances effective learning since students and teachers can communicate conveniently and instantly via online chat rooms and instant messaging software.

LoColms： an innovative approach of enhancing traditional classroom form of education by promoting web-based distance learning in the poorer countries

There have been numerous attempts recently to promote technology based education (Shrestha, 1997) in the poorer third world countries, but so far all these have not provided a sustainable solution as they are either centered and controlled from abroad and relying solely on foreign donors for their sustenance or they are not web-based, which make distribution problematic, and some are not affordable by most of the local population in these places. In this paper we discuss an application, the Local College Learning Management System (LoColms) , which we are developing, that is both sustainable and economical to suit the situation inthese countries. The application is a web-based system, and aims at improving the traditional form of education by empowering the local universities. Its economicability comes from the fact that it is supported by traditional communication technology, the public switching telephone network system, PSTN, which eliminates the need for packet switched or dedicated private virtual networks (PVN) usually required in similar situations. At a later stage, we shall incorporate ontology and paging tools to improve resource sharability and storage optimization in the Proxy Caches (ProCa) and LoColms servers. The system is based on the client/server paradigm and its infrastructure consists of the PSTN, ProCa, with the learning centers accessing the universities by means of point-to-point protocol (PPP) .

Web-based learning in inflammatory bowel diseases:General truths and current specifics

In a field rapidly evolving over the past few years, the management of inflammatory bowel diseases(IBD), Crohn's disease and ulcerative colitis, is becoming in-creasingly complex, demanding and challenging. In the recent years, IBD quality measures aiming to improve patients' care have been developed, multiple new medical therapies have been approved, new treatment goals have been set with the "treat--to--target" concept and drug monitoring has been implemented into IBD clinical management. Moreover, patients are increasingly using Internet resources to obtain information about their health conditions. The healthcare professional with an interest in treating IBD patients should deal with all these challenges in everyday practice by establishing, enhancing and maintaining a strong core of knowledge and skills related to IBD. This is an ongoing process and traditionally these needs are covered with additional reading of textbook or journal articles, attendance at meetings or conferences, or at local rounds. Web--based learning resources expand the options for knowledge acquisition and save time and costs as well. In the new era of communications technology, web-based resources can cover the educational needs of both patients and healthcare professionals and can contribute to improvement of disease management and patient care. Healthcare professionals can individually visit and navigate regularly relevant websites and tailor choices for educational activities according to their existing needs. They can also provide their patients with a few certified suitable internet resources. In this review, we explored the Internet using PubMed and Startpage(Google), for web-based IBD--related educational resources aiming to provide a guide for those interested in obtaining certified knowledge in this subject.

Asynchronous and Synchronous Communication in College English Writing in Web-based Learning Environment

In web-based learning environment,College English writing has always been a thorny issue.Here both asynchronous and synchronous communications in college English writing mean the new interactive teaching belief. This paper attempts to do the blending of two in the traditional writing learning and teaching in college English in order to promote a more flexible,efficient and interactive learning environment in accordance with students' interests and needs.

Lotus LearningSpace在高等特殊教育教学领域的应用

Lotus LearningSpace是Lotus在知识管理策略基础上推出的最新教学解决方案,旨在提供一个可协作、可按计划、辅助指导、分布式的虚拟学习环境。Lotus LearningSpace简体中文版,为国内有关高等特殊教育的研究机构提供了一个很好的参考。斯塔福德郡大学的实验表明,相关软件开发必须要了解各类残疾人群的特点,考虑残疾学生的主要缺陷,开发专门适合残疾学生的、适用领域广泛的虚拟学习系统。

应用Learning Space4实现生理学的远程教育

实现远程教育的关键是有机地组织各类教育资源和高效率的双向通信。 L earning Space4是可以有效地解决高效率有机组织教育资源、跟踪、评估学生的学习状况、非实时和实时教学等关键问题的一个优秀的网络远程教学和管理平台系统。介绍应用 L earning Space4创建远程教育教程的基本方法 ,并以《生理学》第四版为例介绍应用 L

Combination of effective color information and machine learning for rapid prediction of soil water content

Soil water content(SWC)is one of the critical indicators in various fields such as geotechnical engineering and agriculture.To avoid the time-consuming,destructive,and laborious drawbacks of conventional SWC measurements,the image-based SWC prediction is considered based on recent advances in quantitative soil color analysis.In this study,a promising method based on the Gaussian-fitting gray histogram is proposed for extracting characteristic parameters by analyzing soil images,aiming to alleviate the interference of complex surface conditions with color information extraction.In addition,an identity matrix consisting of 32 characteristic parameters from eight color spaces is constituted to describe the multi-dimensional information of the soil images.Meanwhile,a subset of 10 parameters is identified through three variable analytical methods.Then,four machine learning models for SWC prediction based on partial least squares regression(PLSR),random forest(RF),support vector machines regression(SVMR),and Gaussian process regression(GPR),are established using 32 and 10 characteristic parameters,and their performance is compared.The results show that the characteristic parameters obtained by Gaussian-fitting can effectively reduce the interference from soil surface conditions.The RGB,CIEXYZ,and CIELCH color spaces and lightness parameters,as the inputs,are more suitable for the SWC prediction models.Furthermore,it is found that 10 parameters could also serve as optimal and generalizable predictors without considerably reducing prediction accuracy,and the GPR model has the best prediction performance(R^(2)≥0.95,RMSE≤2.01%,RPD≥4.95,and RPIQ≥6.37).The proposed image-based SWC predictive models combined with effective color information and machine learning can achieve a transient and highly precise SWC prediction,providing valuable insights for mapping soil moisture fields.

Automatic Generation of Artificial Space Weather Forecast Product Based on Sequence-to-sequence Model

Both analyzing a large amount of space weather observed data and alleviating personal experience bias are significant challenges in generating artificial space weather forecast products.With the use of natural language generation methods based on the sequence-to-sequence model,space weather forecast texts can be automatically generated.To conduct our generation tasks at a fine-grained level,a taxonomy of space weather phenomena based on descriptions is presented.Then,our MDH(Multi-Domain Hybrid)model is proposed for generating space weather summaries in two stages.This model is composed of three sequence-to-sequence-based deep neural network sub-models(one Bidirectional Auto-Regressive Transformers pre-trained model and two Transformer models).Then,to evaluate how well MDH performs,quality evaluation metrics based on two prevalent automatic metrics and our innovative human metric are presented.The comprehensive scores of the three summaries generating tasks on testing datasets are 70.87,93.50,and 92.69,respectively.The results suggest that MDH can generate space weather summaries with high accuracy and coherence,as well as suitable length,which can assist forecasters in generating high-quality space weather forecast products,despite the data being starved.

Development of New Capabilities Using Machine Learning for Space Weather Prediction

With the development of space exploration and space environment measurements,the numerous observations of solar,solar wind,and near Earth space environment have been obtained in last 20 years.The accumulation of multiple data makes it possible to better use machine learning technique,which has achieved unforeseen results in industrial applications in last decades,for developing new approaches and models in space weather investigation and prediction.In this paper,the efforts on the forecasting methods for space weather indices,events,and parameters using machine learning are briefly introduced based on the study works in recent years.These investigations indicate that machine learning,especially deep learning technique can be used in automatic characteristic identification,solar eruption prediction,space weather forecasting for solar and geomagnetic indices,and modeling of space environment parameters.

Reinforcement learning method for machining deformation control based on meta-invariant feature space

Precise control of machining deformation is crucial for improving the manufacturing quality of structural aerospace components.In the machining process,different batches of blanks have different residual stress distributions,which pose a significant challenge to machining deformation control.In this study,a reinforcement learning method for machining deformation control based on a meta-invariant feature space was developed.The proposed method uses a reinforcement-learning model to dynamically control the machining process by monitoring the deformation force.Moreover,combined with a meta-invariant feature space,the proposed method learns the internal relationship of the deformation control approaches under different stress distributions to achieve the machining deformation control of different batches of blanks.Finally,the experimental results show that the proposed method achieves better deformation control than the two existing benchmarking methods.