Stable Learning via Differentiated Variable Decorrelation

2020 ◽  
Author(s):  
Zheyan Shen ◽  
Peng Cui ◽  
Jiashuo Liu ◽  
Tong Zhang ◽  
Bo Li ◽  
...  
Keyword(s):  
Stable Learning

Fusion based learning approach for predicting concrete pouring productivity based on construction and supply parameters

2016 ◽  
Vol 16 (2) ◽  
pp. 185-202 ◽  
Author(s):  
Mojtaba Maghrebi ◽  
Ali Shamsoddini ◽  
S. Travis Waller
Keyword(s):  
Supply Chain ◽  
Production Rate ◽  
Learning Method ◽  
Data Set ◽  
Content Type ◽  
Field Database ◽  
The Stability ◽  
Stable Learning ◽  
Ready Mixed Concrete ◽  
Practical Implications

Purpose The purpose of this paper is to predict the concrete pouring production rate by considering both construction and supply parameters, and by using a more stable learning method. Design/methodology/approach Unlike similar approaches, this paper considers not only construction site parameters, but also supply chain parameters. Machine learner fusion-regression (MLF-R) is used to predict the production rate of concrete pouring tasks. Findings MLF-R is used on a field database including 2,600 deliveries to 507 different locations. The proposed data set and the results are compared with ANN-Gaussian, ANN-Sigmoid and Adaboost.R2 (ANN-Gaussian). The results show better performance of MLF-R obtaining the least root mean square error (RMSE) compared with other methods. Moreover, the RMSEs derived from the predictions by MLF-R in some trials had the least standard deviation, indicating the stability of this approach among similar used approaches. Practical implications The size of the database used in this study is much larger than the size of databases used in previous studies. It helps authors draw their conclusions more confidently and introduce more generalised models that can be used in the ready-mixed concrete industry. Originality/value Introducing a more stable learning method for predicting the concrete pouring production rate helps not only construction parameters, but also traffic and supply chain parameters.

scholarly journals Online and Stable Learning of Analysis Operators

2019 ◽  
Vol 67 (1) ◽  
pp. 41-53 ◽  
Author(s):  
Michael Sandbichler ◽  
Karin Schnass
Keyword(s):  
Stable Learning

A Probabilistic Classifier System and Its Application in Data Mining

2006 ◽  
Vol 14 (2) ◽  
pp. 183-221 ◽  
Author(s):  
Jorge Muruzábal
Keyword(s):  
Data Mining ◽  
Predictive Power ◽  
Benchmark Problems ◽  
Classifier System ◽  
Probabilistic Classifier ◽  
Classification Tasks ◽  
Representation Language ◽  
Stable Learning ◽  
Well Posed ◽  
Low Uncertainty

The article is about a new Classifier System framework for classification tasks called BYP CS (for BaYesian Predictive Classifier System). The proposed CS approach abandons the focus on high accuracy and addresses a well-posed Data Mining goal, namely, that of uncovering the low-uncertainty patterns of dependence that manifest often in the data. To attain this goal, BYP CS uses a fair amount of probabilistic machinery, which brings its representation language closer to other related methods of interest in statistics and machine learning. On the practical side, the new algorithm is seen to yield stable learning of compact populations, and these still maintain a respectable amount of predictive power. Furthermore, the emerging rules self-organize in interesting ways, sometimes providing unexpected solutions to certain benchmark problems.

Lyapunov stable learning laws for multilayer recurrent neural networks

2021 ◽  
Author(s):  
Alejandro Guarneros-Sandoval ◽  
Mariana Ballesteros ◽  
Ivan Salgado ◽  
Julia Rodríguez-Santillán ◽  
Isaac Chairez
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Stable Learning

Industry-Academic Partnerships in Information Systems Education

2011 ◽  
pp. 264-278
Author(s):  
Mark Conway
Keyword(s):  
Information Systems ◽  
Academic Programs ◽  
Learning Objectives ◽  
Mutual Understanding ◽  
Teaching Resources ◽  
New Employees ◽  
Academic Partnerships ◽  
The University ◽  
Stable Learning ◽  
Incoming Students

Several thousand universities worldwide participate in industry-academic partnerships as a way to expose their students to “real-world” issues and technologies and to provide them skills that will facilitate their transition from the university to the workplace. This chapter highlights several of the leading IT-focused, industry-academic programs such as Hyperion’s Academic Alliance Program, the Teradata University Network, and SAP’s University Alliance Program; and references similar initiatives from Cisco, SUN, and IBM. The focus of the chapter is from an industry practioner’s perspective; it covers what motivates companies to launch these types of programs, what the programs’ goals are, and what benefits accrue to the participating company and university. Information systems and technology (IS&T) are evolving so quickly that universities are continually challenged to keep abreast of the latest developments to ensure that their curricula and programs are current. On one hand, IT programs are pressured by various stakeholders—deans, incoming students, parents, businesses recruiting on campus, and so forth—to keep their programs current and relevant to these constituents’ needs. On the other hand, faculty and IT programs cannot chase the latest fads and each new innovation, if they are to offer a stable learning environment. The significant costs—in terms of time, training, technical support, curriculum revisions, and so forth—involved in deploying commercial software in an academic setting makes selecting which partnerships to pursue an important and far-reaching decision. The benefits can be significant, but the faculty need to understand up front, the expectations and level of commitment needed to make these kinds of collaborations successful. By gaining a better understanding of how industry views these programs, academics will be better able to assess these alliances and determine which best support and align with their programs’ goals and learning objectives. Developing students who can join companies as new employees and IT leaders and quickly contribute to a firm’s success is something that both universities and businesses strive for. But, it requires a mutual understanding of the skills that will be needed, vehicles for developing those skills within the students, and a buy-in from faculty to develop the necessary curriculum and teaching resources. This chapter contends that successfully managed industry-academic partnerships can be a vehicle for developing these capabilities, while enriching learning opportunities for students.

Ambient Pedagogies, Meaningful Learning and Social Software

2010 ◽  
pp. 415-433 ◽  
Author(s):  
Andrew Ravenscroft ◽  
Musbah Sagar ◽  
Enzian Baur ◽  
Peter Oriogun
Keyword(s):  
Digital Age ◽  
Learning Processes ◽  
Social Software ◽  
Learning Design ◽  
Future Trends ◽  
Experience Design ◽  
New Approach ◽  
Dialogue Games ◽  
Ongoing Work ◽  
Stable Learning

This chapter will present a new approach to designing learning interactions and experiences that reconciles relatively stable learning processes with relatively new digital practices in the context of social software and Web 2.0. It will begin with a brief position on current educational articulations of social software before offering some theoretical pointers and methodological perspectives for research and development in this area. The authors will then explain how an ongoing initiative in advanced learning design has developed notions of “ambient learning design” and “experience design” to address these issues and describe a new methodology for developing digital tools that incorporate these concepts. This approach is exemplified through ongoing work within an initiative in Digital Dialogue Games and the InterLoc tool that realises them. Finally, the implications this work has for future trends in designing for inclusive, highly communicative and engaging learning interactions and practices for the digital age are discussed.

Sign in / Sign up

Export Citation Format

Share Document