Optimizing Model Training in Interactive Learning Scenarios

2021 ◽  
pp. 156-165
Author(s):  
Davide Carneiro ◽  
Miguel Guimarães ◽  
Mariana Carvalho ◽  
Paulo Novais
Keyword(s):  
Interactive Learning ◽  
Learning Scenarios ◽  
Model Training ◽  
Optimizing Model

scholarly journals Privacy-Preserving Federated Learning Framework with General Aggregation and Multiparty Entity Matching

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Zhou Zhou ◽  
Youliang Tian ◽  
Changgen Peng
Keyword(s):  
Data Privacy ◽  
Privacy Preserving ◽  
Entity Matching ◽  
Learning Framework ◽  
Learning Tasks ◽  
Learning Scenarios ◽  
Model Training ◽  
Logistic Regression Algorithm ◽  
Shamir Secret Sharing ◽  
Training And Support

The requirement for data sharing and privacy has brought increasing attention to federated learning. However, the existing aggregation models are too specialized and deal less with users’ withdrawal issue. Moreover, protocols for multiparty entity matching are rarely covered. Thus, there is no systematic framework to perform federated learning tasks. In this paper, we systematically propose a privacy-preserving federated learning framework (PFLF) where we first construct a general secure aggregation model in federated learning scenarios by combining the Shamir secret sharing with homomorphic cryptography to ensure that the aggregated value can be decrypted correctly only when the number of participants is greater than t . Furthermore, we propose a multiparty entity matching protocol by employing secure multiparty computing to solve the entity alignment problems and a logistic regression algorithm to achieve privacy-preserving model training and support the withdrawal of users in vertical federated learning (VFL) scenarios. Finally, the security analyses prove that PFLF preserves the data privacy in the honest-but-curious model, and the experimental evaluations show PFLF attains consistent accuracy with the original model and demonstrates the practical feasibility.

scholarly journals Interactive Learning of Dialog Scenarios from Examples

2020 ◽  
Author(s):  
Daiga Deksne ◽  
Raivis Skadiņš
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Interactive Learning ◽  
Neural Model ◽  
Action Prediction ◽  
The Public ◽  
Dialog System ◽  
The Neural Network ◽  
Model Training

This paper reports on the development of a toolkit that enables collecting dialog corpus for end-to-end goal-oriented dialog system training. The toolkit includes the neural network model that interactively learns to predict the next virtual assistant (VA) action from the conversation history. We start with exploring methods for VA dialog scenario learning from examples after we perform several experiments with the English DSTC dialog sets in order to find the optimal strategy for neural model training. The chosen algorithm is used for training the next action prediction model for the Latvian dialogs in the public transport inquiries domain collected using the platform. The accuracy for the English and the Latvian dialog models is similar – 0.84 and 0.86. This shows that the chosen method for neural network model training is language independent.

PENGEMBANGAN MEDIA PEMBELAJARAN INTERAKTIF TEKNIK PEMESINAN BUBUT

2020 ◽  
Vol 6 (2) ◽  
pp. 169
Author(s):  
Philip Nababan ◽  
Efendi Napitupulu ◽  
R Mursid
Keyword(s):  
Student Learning ◽  
Learning Outcomes ◽  
Interactive Learning ◽  
Descriptive Analysis ◽  
Student Learning Outcomes ◽  
Field Trials ◽  
Student Responses ◽  
Analysis Techniques ◽  
Qualitative Descriptive

Abstrak: Penelitian ini bertujuan untuk: (1) Mengetahui tanggapan siswa terhadap kualitas media pembelajaran interaktif pada pembelajaran Teknik Pemesinan Bubut. (2) Mengetahui keefektifan media pembelajaran interaktif pada pembelajaran Teknik Pemesinan Bubut pada siswa program keahlian Teknik Pemesinan. Jenis penelitian ini adalah penelitian pengembangan. Data tentang kualitas produk pengembangan ini dikumpulkan dengan angket dan dianalisis dengan teknik analisis deskriptif kualiatatif. Hasil penelitian menunjukkan bahwa; (1) uji ahli materi pelajaran Teknik Pemesinan Bubut berada pada kualifikasi sangat baik (88,92%), (2) uji ahli desain pembelajaran berada pada kualifikasi sangat baik (85,21%), (3) uji ahli rekayasa perangkat lunak berada pada kualifikasi sangat baik (84,03%), (4) uji coba perorangan berada pada kualifikasi sangat baik (88,75%), (5) uji coba kelompok kecil berada pada kualifikasi sangat baik (91,35%) dan (5) uji coba lapangan berada pada kualifikasi sangat baik (88,31%). Hasil pengujian hipotesis membuktikan bahwa terdapat perbedaan antara hasil belajar siswa yang menggunakan media pembelajaran interaktif  dengan hasil belajar siswa yang menggunakan buku teks. Hal ini ditunjukkan dengan hasil pengolahan data diperoleh  thitung sebesar 4,68 dan ttabel sebesar 1,67 pada taraf kepercayaan 95 persen. Maka diperoleh bahwa thitung> ttabel. Disimpulkan bahwa  hasil belajar siswa yang menggunakan media pembelajaran interaktif dengan efektifitas sebesar 72,77 %. lebih tinggi dari hasil belajar siswa yang diajar dengan pembelajaran menggunakan buku teks dengan efektifitas sebesar 62,13%. Kata Kunci: media pembelajaran interaktif, teknik pemesinan bubut Abstract: This study aims to: (1) Determine student responses to the quality of interactive learning media on learning Lathe Machining Techniques. (2) Knowing the effectiveness of interactive learning media on learning of Machining Lathe in students of Machining Engineering expertise program. This type of research is development research. Data about the quality of this development product was collected by a questionnaire and analyzed by qualitative descriptive analysis techniques. The results showed that; (1) Lathe machining engineering subject matter expert test is in very good qualification (88.92%), (2) learning design expert test is in very good qualification (85.21%), (3) software engineering expert test is in in very good qualifications (84.03%), (4) individual trials were in very good qualifications (88.75%), (5) small group trials were in very good qualifications (91.35%) and (5 ) field trials are in very good qualifications (88.31%). Hypothesis testing results prove that there are differences between student learning outcomes using interactive learning media with student learning outcomes using textbooks. This is indicated by the results of data processing obtained by tcount of 4.68 and ttable of 1.67 at a confidence level of 95 percent. Then it is obtained that tcount> ttable. It was concluded that student learning outcomes using interactive learning media with an effectiveness of 72.77%. higher than student learning outcomes taught by learning to use textbooks with an effectiveness of 62.13%. Keywords: interactive learning media, lathe machining techniques

Smart mature resilience, system dynamics based interactive learning environment: A beta version

2017 ◽  
Vol 7 (3) ◽  
pp. 367-379
Author(s):  
Marta Iturriza ◽  
Ahmed A. Abdelgawad ◽  
Leire Labaka ◽  
Jaziar Radianti ◽  
Jose M. Sarriegi ◽  
...  
Keyword(s):  
Learning Environment ◽  
System Dynamics ◽  
Interactive Learning ◽  
Interactive Learning Environment ◽  
Beta Version

“Analytical Techniques for Development Planning” (A Review Of Tims' Multisector Model For Pakistan'S Third Plan (1965-70))

1968 ◽  
Vol 8 (2) ◽  
pp. 240-263
Author(s):  
Azizur Rahman Khan
Keyword(s):  
Analytical Techniques ◽  
Development Planning ◽  
General Idea ◽  
Relative Prices ◽  
Scarce Resources ◽  
Sectoral Output ◽  
Consistency Model ◽  
Present Decade ◽  
Optimizing Model ◽  
Multisector Model

In the present decade there has been a great proliferation of multisectoral models for planning. Part of the incentive has certainly been the potentiality of their application in formulating the actual plans. By now there have been so many different types of multisectoral models that it is useful to attempt some kind of classification according as whether or not they embody certain well-known features. The advantage of such a classification is that one gets a general idea about the structure of the model simply by knowing where it belongs in the list of classification. One broad principle of classification is based on whether the model simply provides a consistent plan or whether it also satisfies some criteria of optimality. A multisectoral consistency model provides an allocation of the scarce resources (e.g., investment and foreign exchange) in such a way that the sectoral output levels are consistent with some given consumption or income target, consistency in this context meaning that the supply of each sector's output is matched by demand generated by intersectoral and final use at base-year relative prices. To the extent that the targets are flexible, there may be many such feasible plans. An optimizing model finds the "best" possible allocation of resources among sectors, the "best" being understood in the sense of maximiz¬ing > a given preference function subject to the constraints that ensure that the plan is also feasible.

The Training of the Fufure Teachers of Ukrainian Language and Literature by Means of Interactive Studying Techniques

2020 ◽  
pp. 248-269
Author(s):  
Tetiana Rybchenko Keser
Keyword(s):  
Higher Education ◽  
Interactive Learning ◽  
Educational Institution ◽  
Learning Technologies ◽  
Educational Process ◽  
Project Work ◽  
Future Teachers ◽  
Learning Methods ◽  
Main Research ◽  
Language And Literature

The article focuses on the theoretical and methodological aspects of the use of interactive learning and its advantages over traditional learning. The use of interactive learning in both secondary and higher education is analyzed. The research goal is to theoretically substantiate and highlight the introduction of methods of the model of training future Ukrainian language and literature teachers by means of interactive learning technologies, as well as to determine the factors of their choice. The main research methods used were analysis, generalization and modeling, observation, synthesis, systematization. The results of the conducted research allowed the author to reveal the qualities that a future teacher of Ukrainian language and literature should possess; to describe some pedagogical problems of training the future teachers of Ukrainian language and literature by means of interactive learning technologies.The benefit of this study is the defined content of interactive learning, which is believed to be a specially organized comfortable mutual learning of participants of the educational process as equal its subjects, which provides for their continuous active interaction, during which each of the students realizes and reflects all its knowledge and actions, feels successful and intellectually capable. The author identified such interactive learning methods of the model of training future teachers of Ukrainian language and literature in higher education institutions as: trainings, educational discussions; game technologies; interactive lectures: problem lectures, lecture-visualization, binary lecture, lecture-press conference, round table, cases, brainstorming. Moreover, the most used interactive learning methods of training future teachers of Ukrainian language and literature in universities are given and theoretically grounded; they are training, discussion, role playimg, method of «Spoiled phone», method of «remote project work Minecraft», «Сourt hearing», «Augmented reality», use of presentations. The author highlights their introduction into the work of the National Pedagogical Dragomanov University, states the positive aspects of interactive learning compared to classical one, determines seven factors for the choice of methods. As a result the author makes a conclusion that the use of interactive technologies not only contributes to the creation of an atmosphere of cooperation and mutual understanding in the educational institution, but also implements the basic principles of personality-oriented learning.

Sign in / Sign up

Export Citation Format

Share Document