We think you have liked this presentation. If you wish to download it, please recommend it to your friends in any social system. Share buttons are a little bit lower. Thank you!
Presentation is loading. Please wait.
Published byAngel Leap
Modified about 1 year ago
Increasing Completion of Neural Networks Coursework- 1 Presented at CIS 2011 © Dr Richard Mitchell 2011 Increasing Completion of Neural Networks Coursework Dr Richard Mitchell Senior Lecturer and University Teaching Fellow Cybernetics Research Group School of Systems Engineering University of Reading, UK
Increasing Completion of Neural Networks Coursework- 2 Presented at CIS 2011 © Dr Richard Mitchell 2011 Overview Part 2 module on Neural Networks assessment : Implement an Object Oriented Neural Network Complete suitable specified hierarchy Apply it to real world problem of students own choice Problem Significant numbers not completing work (up to 33%) Some not apply network; some not even implement NN Paper Describes strategies employed to overcome This year 95% completed work
Influences for Approach Feedback effective if students act on it to improve on future work and learning Glover and Brown Most likely if Feedback frequent, timely, sufficiently detailed Feedback linked to purpose of assessment Feedback understandable by students Focus on learning by relating to future work Gibbs and Simpson Increasing Completion of Neural Networks Coursework- 3 Presented at CIS 2011 © Dr Richard Mitchell 2011
Increasing Completion of Neural Networks Coursework- 4 Presented at CIS 2011 © Dr Richard Mitchell 2011 Nomenclature in Multi Layer Net x 2 (2) f x1x1 1 1 w2w2 x 2 (1) 2 (1) 2 (2) 2 (3) x 2 (3) w 2,3 f f w 2,2 w 2,1 Data In x 3 (2) x2x2 w3w3 x 3 (1) 3 (1) 3 (2) f f w 3,2 w 3,1 x3x3 Data Out x m outputs layer m w m weights layer m m deltas layer m Program with objects for each layer, not each neuron:
Relevant Equations – for each layer Increasing Completion of Neural Networks Coursework- 5 Presented at CIS 2011 © Dr Richard Mitchell 2011 Some commonality in functions / data : so o-o approach sensible
Increasing Completion of Neural Networks Coursework- 6 Presented at CIS 2011 © Dr Richard Mitchell 2011 Hierarchy SingleLinearLayer complete network able to compute / learn data + calc its weighted deltas SingleSigmoidalLayer inherits, own Calc Outputs / Delta MultiSigmoidalLayer hidden layer plus pointer to next So is multilayer network Most of its functions 2 lines - process own layer and next MultiSigmoidal Class Base SingleLinear SingleSigmoidal
Classes Increasing Completion of Neural Networks Coursework- 7 Presented at CIS 2011 © Dr Richard Mitchell 2011 SingleLinearLayer numInputs, numNeurons, numWeights; outputs, deltas, weights, wtchanges; CalcOutputs(inputs); FindDeltas (targets); ChangeAllWeights(inputs, lparas) PrevLayersErrors(errors) Constructor (numIn, numOut); Destructor; ComputeNetwork(data); AdaptNetwork(data, lparas); SetTheWeights(initWts); ReturnTheWeights(theWts); SingleSigmoidaLayer CalcOutputs(inputs); FindDeltas (targets); ErrorsToDeltas(); Constructor (numIn, numOut); Destructor; MultiSigmoidalLayer nextLayer; CalcOutputs(inputs); FindDeltas (targets); ChangeAllWeights(inputs, lparas) Constructor (numIn, numOut, nxt); Destructor; SetTheWeights(initWts); ReturnTheWeights(theWts); Shows name, protected parts (data + functions) and public interface
Strategies for Better Completion Increasing Completion of Neural Networks Coursework- 8 Presented at CIS 2011 © Dr Richard Mitchell 2011 For developing the neural network Divide into series of tasks – back up help via VLE Better, have 3 lab sessions two weeks apart Demonstrator help in lab Students copy code/results into template document Easily marked, direct relevant feedback Students make corrections before next lab For application Students have working network by Spring term Five weeks to apply problem, investigate data processing, different structures, etc Write up as conference paper not report
Tasks in Lab Sessions Increasing Completion of Neural Networks Coursework- 9 Presented at CIS 2011 © Dr Richard Mitchell )Lab 1 : Complete SingleLinear; write SingleSigmoidal Create Project from provided files : familiarisation Simple change, write function to return weights in net Write code so network can learn Write functions for SingleSigmoidal 2)Lab 2 : Write MultiSigmoidal Develop the MultiSigmoidal Investigate changing network size / learning paras 3)Lab 3 : Complete MLP – edit main program So learn using train, validation and unseen data sets Investigate changing network size / learning paras
Completion Rates Increasing Completion of Neural Networks Coursework- 10 Presented at CIS 2011 © Dr Richard Mitchell 2011 YearClass size Students reporting their application Students completing MLP 2010/ / / /8* * 2007/8 No lab sessions, but students allowed to use another’s MLP for application
Reflections Increasing Completion of Neural Networks Coursework- 11 Presented at CIS 2011 © Dr Richard Mitchell 2011 Discussions with students and demonstrators show lab sessions beneficial : help provided when needed; students self help Students requested to reflect on comments also good Consistent with Hughes : “improved coursework submission attributed to learner motivation from peer/tutor support” Rapid relevant feedback also appreciated Short conference paper, less work than report; ‘sold to students’ as learning opportunity as they will write paper as part of assessment for Part 3 and 4 project
Increasing Completion of Neural Networks Coursework- 12 Presented at CIS 2011 © Dr Richard Mitchell 2011 Conclusions and Further Work Coursework provides good practical example of object orientation, applied to neural networks Good use of encapsulation, small interface, inheritance Staged tasks and rapid feedback help more to complete the neural network Conference paper seems to have worked well re completion of complete assignment + good skill to have Easier to mark – more time for giving feedback Author to see if similar approaches can be used to better assess whether students ‘engaging’ in Part 1 – as used in ‘Engagement system for Retention’.
Assessment and feedback Principles, practice and technologies.
On Simple Adaptive Momentum - 1 Presented at CIS 2008 © Dr Richard Mitchell 2008 On Simple Adaptive Momentum Dr Richard Mitchell Cybernetics Intelligence.
2010 Department of Automatic Control and Systems Engineering Student engagement with MATLAB and supporting independent learning J A Rossiter University.
Creating a dialogue over feedback between staff and students in the classroom and online Heather A. Thornton
Using Learning Outcomes and Assessment Criteria Peter Noakes Department of Electronic Systems Engineering University of Essex.
Dr Karen King, Institute of Agri-food and Land Use and Centre of Excellence in Teaching and Learning, Biosciences. School of Biological Sciences.
UNIT 5 ASSESSMENT AND FEEDBACK MODULE 2 - FEEDBACK Dr Helen Boulton, Nottingham Trent University.
The Cost of Authoring with a Knowledge Layer Judy Kay and Lichao Li School of Information Technologies The University of Sydney, Australia.
Assessment which works: Enhancing student learning without killing the tutors Prof. Sue Bloxham
Self- and Peer-Assessment Rationale Preparation Tasks Implementation Evaluation.
Effective Assessment and Feedback Rebecca Rhodes.
111 How do I link Learning Outcomes to Teaching and Learning Activities and Assessment? 20 March 2014 University College Cork Dr Declan Kennedy,
Introduction to CDIO: Key Features & Components Dennis Sale Senior Education Advisor Singapore Polytechnic.
Analyzing Student Work Robert V. Jervis Consultant for the Council of Chief Staff School Officers Comprehensive Social Studies Assessment Project.
Feedback sessions - Helping first year students get the most out of assessment and feedback Sue R Whittle & Linda B Bonnett Faculty of Biological Sciences.
Learning Center 6 Teacher Feedback A powerpoint borrowed from the Georgia State Department of Education.
P1 RJM 13/03/08For IEEE Colloquium Control Education, Sheffield © Dr Richard Mitchell 2008 Modeling Project at Reading Dr Richard Mitchell and Dr Will.
Curriculum for Excellence: Design of New National Courses Feedback from Engagement with Colleges Dr John Allan SQA.
T B L in college English teaching. What is your teaching style? PPresentation PPractice PProduction.
The Validation Planning Process The EUROCONTROL Validation Planning Process A brief presentation on the outcome of TRS139/04 Presentation Prepared by:
PhDs in Computer Science (FAIRS09) Frans Coenen Monday 14 December 2009 Department of Computer Science The University of Liverpool
Learner-Centered Teaching Elizabeth Normandy Teaching and Learning Center.
Designing Data Resources: Tools for the provision of interactive research data management workshops IDCC13 Workshop, Amsterdam.
Dr Alison Williams (& Dr Simon Tate) Geography. Outline The Geography dissertation process The problem Solutions to date and issues with these Further.
Introduction to Java 2 Programming Lecture 1 Java, Principles of OO, UML.
Teaching first and second language acquisition Nigel Duffield & Ayumi Matsuo School of English Literature, Language and Linguistics, University of Sheffield.
Part I: The 3 Ts of Online Assessment: Tools, Techniques, and (Saving) Time Curtis J. Bonk, Professor, Indiana University President, CourseShare
Margaret Home, Dianne McNab MARCET, L&LS Michelle Walker Subject & Liaison, L&LS.
Metrics for Physical Science The Easy Way: The Easy Way: Learning Learning the Metric System and Conversions the Metric System and Conversions Utilizing.
A Masters in Education in eLearning The University of Hull.
© 2016 SlidePlayer.com Inc. All rights reserved.