63,686 Hits in 4.5 sec

Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals

Daniel Tanneberg, Jan Peters, Elmar A. Rückert
2017 Conference on Robot Learning  
The efficient online adaptation is shown in simulation by learning an unknown workspace constraint using mental replay and cognitive dissonance as intrinsic motivation signal.  ...  This fast adaptation behavior allows the robot to learn from only a small number of physical interactions and is a promising feature for reusing the model in different environments.  ...  We will show that as a result of these mechanisms, the model can efficiently adapt online to unknown environments.  ... 
dblp:conf/corl/Tanneberg0R17 fatcat:svjzu3naizbojmtj24ongeqsje

Source Code Editing Evaluator for Learning Programming

Timotius Nugroho Chandra, Inggriani Liem
2013 Procedia Technology - Elsevier  
In this paper, we emphasize on source code editing environment named Doppel and Ganger (D&G). D&G is a web based application aimed for monitoring coding process by recording typing activities.  ...  Although most students have personal computing devices, those devices have various specifications that create difficulties in evaluation.  ...  Acknowledgements We would like to thank Karol Danutama for providing an opportunity to collaborate via Oddysseus.  ... 
doi:10.1016/j.protcy.2013.12.177 fatcat:dtu6kr4f6jfcnhqybevn4axohm

Online learning for characterizing unknown environments in ground robotic vehicle models

Alec Koppel, Jonathan Fink, Garrett Warnell, Ethan Stump, Alejandro Ribeiro
2016 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
Since the relationship between the feature space and decision variable is highly nonlinear, we solve this problem using online task-driven dictionary learning methods.  ...  We consider the problem of learning unmodelled dynamics or environmental effects on a ground robotic vehicle for the purpose of incorporating this information into path-planning strategies.  ...  In order to develop control strategies which are adaptive to unknown operating environments and able to operate with on-board sensors and information processing capabilities only, the robot must learn  ... 
doi:10.1109/iros.2016.7759118 dblp:conf/iros/KoppelFWSR16 fatcat:vl5hdpn5jvgulmb5jl6l7fytfm

A Brief Review of Neural Networks Based Learning and Control and Their Applications for Robots

Yiming Jiang, Chenguang Yang, Jing Na, Guang Li, Yanan Li, Junpei Zhong
2017 Complexity  
As an imitation of the biological nervous systems, neural networks (NNs), which have been characterized as powerful learning tools, are employed in a wide range of applications, such as control of complex  ...  This article aims to bring a brief review of the state-of-the-art NNs for the complex nonlinear systems by summarizing recent progress of NNs in both theory and practical applications.  ...  Therefore, the NN are used to approximate the unknown dynamics f  M (q)q   C(q , q)q   G(q) and to improve the performance of the system via the online estimation.  ... 
doi:10.1155/2017/1895897 fatcat:t4rq6ux7brhnjicextnyh5o6dq


Andrej Maras
2021 SOCIETY INTEGRATION EDUCATION Proceedings of the International Scientific Conference  
in virtual classrooms and online forums.  ...  Participants' statements indicate that during online teaching students most often communicated with their teachers via e-mail, WhatsApp, Zoom, Google Classroom, and Teams.  ...  Computer-assisted learning implies an individual form of learning in which an individual uses certain learning programs with the help of the media and computers.  ... 
doi:10.17770/sie2021vol5.6217 fatcat:cemduswn4jh37abqia7abivgju

Computer-aided learning in artificial neural networks

J.V. Ringwood, G. Galvin
2002 IEEE Transactions on Education  
Index Terms-Artificial neural networks (ANNs), computer-aided learning (CAL), MATLAB, online learning, World Wide Web (WWW).  ...  This paper describes the development and evaluation of a computer-aided learning (CAL) package for a graduate course in artificial neural networks (ANNs).  ...  and the interaction between classmates can be very beneficial [15] . 4) The competitive environment: The classroom environment can be beneficial in motivating students to learn course material.  ... 
doi:10.1109/te.2002.804401 fatcat:5vzsb2xltjestoypfu7tljrhgq

Off-Policy Recommendation System Without Exploration [chapter]

Chengwei Wang, Tengfei Zhou, Chen Chen, Tianlei Hu, Gang Chen
2020 Lecture Notes in Computer Science  
Empirical studies show that the proposed method outperforms state-of-the-art techniques on both offline and simulated online environments.  ...  To fulfill these requirements, we devise a novel method name Generator Constrained Q-learning (GCQ). GCQ additionally trains an action generator via supervised learning.  ...  Stage one: compute the signal matrix C t via the following recurrence.  ... 
doi:10.1007/978-3-030-47426-3_2 fatcat:ajyhh544vzedhgyqee7bjxaipy

Preschool and early primary school age children learning of computational thinking through the use of asynchronous learning environments in the age of Covid-19

Evaggelia Skaraki, Department of Preschool Education, University of Crete, Crete, Greece, Fotios Kolokotronis, Department of Primary Education, University of Crete, Crete, Greece
2022 Advances in Mobile Learning Educational Research  
environments in the age of covid.  ...  Over the past few years in Greece, a sharp rise in computational thinking has been noted as both students and teachers feel the need to create more imaginative and interactive ways.  ...  In addition, young students can use Web-based programming environments in programming and the development of CT such as Kodable and the section for children who do not know how to read via the use of special  ... 
doi:10.25082/amler.2022.01.002 fatcat:mqqfrfvjr5chfabhebzzdq6x2u

Adapting the Obtrusiveness of Service Interactions in Dynamically Discovered Environments [chapter]

William Van Woensel, Miriam Gil, Sven Casteleyn, Estefanía Serral, Vicente Pelechano
2013 Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering  
across previously unknown, dynamically discovered environments.  ...  We supply a mobile user interface for defining situations, and validate it via an initial study with end-users.  ...  This work has been developed with the support of MICINN under the project EVERYWARE TIN2010-18011 and co-financed with ERDF, in the grants program FPU.  ... 
doi:10.1007/978-3-642-40238-8_21 fatcat:tdgfcqfcbvg3lddp2h2ocux4z4

VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning

Luisa M. Zintgraf, Sebastian Schulze, Cong Lu, Leo Feng, Maximilian Igl, Kyriacos Shiarlis, Yarin Gal, Katja Hofmann, Shimon Whiteson
2021 Journal of machine learning research  
Trading off exploration and exploitation in an unknown environment is key to maximising expected online return during learning.  ...  In two toy domains, we illustrate how variBAD performs structured online exploration as a function of task uncertainty.  ...  in an initially unknown environment, while learning, within the horizon H + .  ... 
dblp:journals/jmlr/ZintgrafSLFISGH21 fatcat:tcwij2jelndcfhqcnqaaw5ax6i

Emergency Remote Support at the Self-Access Learning Center: Successes and Limitations

Tetsushi Ohara, Fumie Ishimura
2020 Studies in Self-Access Learning Journal  
We find that ERS at the SALC can sufficiently provide students with individual support in learning and practicing languages as well as some psychological support via a videoconferencing tool.  ...  However, we also identify that ERS cannot create an environment for socialization and social learning compared to the usual SALC in which students gather and socialize with others freely while developing  ...  His research interests include learner autonomy in language learning, roles of self-access learning centers, and active learning activities for the classroom.  ... 
doi:10.37237/110310 fatcat:jnqqwhmtrne3bhee3gmo2bvsvq

Improving Communicative Competence through Synchronous Communication in Computer-Supported Collaborative Learning Environments: A Systematic Review

Xi Huang
2018 Education Sciences  
collaborative learning environments in service of communicative competence.  ...  place between human beings via the instrumentality of computers in forms of text, audio and video communication, such as live chat and chatrooms as socially-oriented meaning construction.  ...  in the current version of the paper.  ... 
doi:10.3390/educsci8010015 fatcat:enyhebvoarbf7odamxsir7gfka

RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes [article]

Salman Habib, Allison Beemer, Joerg Kliewer
2021 arXiv   pre-print
The main idea behind RELDEC is that an optimized decoding policy is subsequently obtained via reinforcement learning based on a Markov decision process (MDP).  ...  In this work we propose RELDEC, a novel approach for sequential decoding of moderate length low-density parity-check (LDPC) codes.  ...  Moreover, MAML has been used for channel coding based on few pilot transmission in [35] , where the focus is on learning a decoder for a fixed encoder via supervised learning.  ... 
arXiv:2112.13934v1 fatcat:mksizrwc3fcg3l3eurtwvly6ei

Mobile Computing Systems Programming: A Graduate Distributed Computing Course

Lars Kulik
2007 IEEE Distributed Systems Online  
a key emerging area in mobile computing applications).  ...  The SUM lab is open to students enrolled in MCSP or Sensor Networks and Applications and to all research students working in sensor networks, pervasive and ubiquitous computing, mobile computing, and distributed  ... 
doi:10.1109/mdso.2007.27 fatcat:33vyrhokg5evtlqaq5eouosmya

VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning [article]

Luisa Zintgraf, Kyriacos Shiarlis, Maximilian Igl, Sebastian Schulze, Yarin Gal, Katja Hofmann, Shimon Whiteson
2020 arXiv   pre-print
Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning.  ...  In this paper, we introduce variational Bayes-Adaptive Deep RL (variBAD), a way to meta-learn to perform approximate inference in an unknown environment, and incorporate task uncertainty directly during  ...  Maximilian Igl is supported by the UK EPSRC CDT in Autonomous Intelligent Machines and Systems. Sebastian Schulze is supported by Dyson.  ... 
arXiv:1910.08348v2 fatcat:tzfn3oig2rea7dby3e45npcija
« Previous Showing results 1 — 15 out of 63,686 results