7088CEM Artificial Neural Networks
[ad_1]
This document is for Coventry University students for their own use in completing their
assessed work for this module and should not be passed to third parties or posted on any
website. Any infringements of this rule should be reported to
facultyregistry.eec@coventry.ac.uk.
Faculty of Engineering, Environment and Computing
7088CEM Artificial Neural Networks
Assignment Brief 2019/20
| Module Title Artificial Neural Network |
Individual/Group Project (2 people), but individual paper submission. |
Cohort May. |
Module Code 7088CEM |
| Coursework Title (e.g. CWK1) CW |
Hand out date: 8.6.2020 |
||
| Lecturer: Dr Sara Sharifzasdeh | Due date: 10.7.2020 18:00 |
||
| Estimated Time (hrs): 25 Word Limit*: 6 pages A4, up to 4500 |
Coursework type: Individual report (in academic paper form in 6 pages) |
% of Module Mark 100% |
|
| Submission arrangement online via Aula. File types and method of recording: Submit your report as a PDF or Word document using the ‘Assignment’ link in the 7088CEM Aula space. Mark and Feedback date (DD/MM/YY): TBC Mark and Feedback method (e.g. in lecture, written via Gradebook): TBC |
| Module Learning Outcomes Assessed: 1. Acquire a deep knowledge of the constitutional concepts of artificial neural networks including their biological inspiration. 2. Apply and compare the different architectures and learning approaches available in neural network systems. 3. Design and develop different neural network models applying appropriate learning approaches for real world applications. 4. Use the available neural network simulators, develop solutions to real-world problems and appraise their limitations. 5. Critically evaluate the trends in neural network developments. |
| Task and Mark distribution: In this assignment, you will have to select a problem (e.g., a classification, prediction, modelling or clustering problem), ideally inspired from the real world, and explore how best to apply neural network learning algorithms to solve it. If you want to challenge yourself, you can choose either more recent and advanced modelling approaches in neural networks (such as deep neural networks) and/or more difficult applications, e.g., more complex problems from image processing, signal processing, information retrieval, natural language processing, biology. You should first discuss with your tutor to make sure that the problem is challenging enough. The main purpose of this assignment is to: • Test the understanding on fundamental concepts of neural networks and their applications. |
This document is for Coventry University students for their own use in completing their
assessed work for this module and should not be passed to third parties or posted on any
website. Any infringements of this rule should be reported to
facultyregistry.eec@coventry.ac.uk.
| • Perform appropriate preparation of a data set and evaluate the performance of different neural network algorithms on the chosen data set(s). • Gain practical experience in using neural network learning algorithms for solving a real-life (classification/clustering/prediction) problem. • Demonstrate your ability to critically evaluate the results and compare different learning algorithms and their results. |
| Notes: 1. Please notify your registry course support team and module leader for disability support. 2. Any student requiring an extension or deferral should follow the university process as outlined here. 3. The University cannot take responsibility for any coursework lost or corrupted on disks, laptops or personal computer. Students should therefore regularly back-up any work and are advised to save it on the University system. 4. If there are technical or performance issues that prevent students submitting coursework through the online coursework submission system on the day of a coursework deadline, an appropriate extension to the coursework submission deadline will be agreed. This extension will normally be 24 hours or the next working day if the deadline falls on a Friday or over the weekend period. This will be communicated via email and as an Aula announcement. 5. You are encouraged to check the originality of your work by using the Turnitin links in Aula space. (A percentage of similarity higher than 30% is encouraged to be avoided and is recommended a resubmission after amendments). 6. Collusion between students (where sections of your work are similar to the work submitted by other students in this or previous module cohorts) is taken extremely seriously and will be reported to the academic conduct panel. 7. If you make use of the services of a proof reader in your work you must keep your original version and make it available as a demonstration of your written efforts. 8. You must not submit work for assessment that you have already submitted (partially or in full), either for your current course or for another qualification of this university, unless this is specifically provided for in your assignment brief or specific course or module information. Where earlier work by you is citable, ie. it has already been published/submitted, you must reference it clearly. Identical pieces of work submitted concurrently will also be considered to be self-plagiarism. |
| Weighting: 100% of Coursework component Deadline: 10.7.2020 18:00. Submission: Submit your report as a pdf using the ‘Assignment’ link in the 7088CEM space in Aula. This is an individual piece of work. This assignment requires you to analyse some data and put your findings in a report. You will be required to: |
This document is for Coventry University students for their own use in completing their
assessed work for this module and should not be passed to third parties or posted on any
website. Any infringements of this rule should be reported to
facultyregistry.eec@coventry.ac.uk.
| • Ideally work in groups of 2, but each group member must develop an individual project report. If you are working in a group of two, you need to consider developing at least one common methodology and one individual techniques for your analysis. For individual groups, at least two different analysis methods must be applied and compared. • Actively participate in all activities; • Consult with your tutor about your project work if needed during the lab sessions. You will write a proposal (maximum of 1 A4 page), giving the title of the project, the names of all group members, the description of the problem and the plan of the work. You will need to submit this proposal to your tutor by Tuesday 16th June via 7088CEM Aula feed space. In case of any required changes, you will receive feedback from your tutor. Any questions about your work can be raised in the two follow-up sessions on 17th June 13-15 and 24th June 13-15 to be held online via MSTeams. Your final submission will include a scientific paper (in 6 pages A4, up to 4500 words), written individually based on the experience and the results gained during the group work. You will have to acknowledge the contributions of all group members in your paper. You are encouraged to target a certain conference or journal and submit the proposed paper to it. Submission guidelines can be found on the conference or journal web page you choose to submit to. List of reputed conferences and journals: o IJCNN Conference o NIPS Conference o International Conference of Machine Learning o Machine Learning Journal o Neural Networks Journal o Others (please let us know) The paper should broadly include the following sections: 1. Abstract; 2. Introduction (where you introduce the problem along a short literature review of related work; if the literature review is longer it is recommended to be a section on its own); 3. Problem and Data set(s) description (where you describe in detail the problem you want to solve and its significance); 4. Methods (where you shortly describe the neural network methods and/or other methods employed to solve the problem); 5. Experimental setup (including data pre-processing, feature selection and extraction); 6. Results; 7. Discussion and Conclusions; 8. References These are generic section titles, which you may adapt appropriately to the application/problem that is being investigated. You may include sections describing modifications of algorithms or developments that are novel and specific to your work. You may include figures, tables, pseudo-code, and appendices with the actual code that has been developed. |
This document is for Coventry University students for their own use in completing their
assessed work for this module and should not be passed to third parties or posted on any
website. Any infringements of this rule should be reported to
facultyregistry.eec@coventry.ac.uk.
| More information of how to write a paper is available at the following link: https://www.semanticscholar.org/paper/Crafting-Papers-on-Machine-Learning Langley/3efcb97c1de1c87832a7a1d99e91801992a938ec , “Crafting Papers on Machine Learning” by Pat Langley. You will need to follow the formatting guidelines of the IEEE Manuscript Template for Conference Proceedings (A4) http://www.ieee.org/conferences_events/conferences/publishing/templates.html. The group project and the milestones: • Working in groups of maximum 2, you have to select a challenging real world problem and one (or more) appropriate data set(s) as suggested above. You may also use the following links, which have numerous problems and data sets: UCI Machine Learning Repository: http://archive.ics.uci.edu/ml/; ICML papers: http://icml.cc/2012/papers/; Kaggle competitions: http://www.kaggle.com/competitions; Stanford machine learning projects: http://cs229.stanford.edu/projects2013.html , http://cs229.stanford.edu/projects2012.html, http://cs229.stanford.edu/projects2011.html, • Next, you have to select, implement and apply appropriate neural network learning algorithms to solve the problem, perform appropriate data processing, if needed, and record the results from the experiments. You will write a proposal (maximum of 1 A4 page), giving the title of the project, the names of all group members, the description of the problem and the plan of the work. You will need to submit this proposal to your tutor by Tuesday 16th June via 7088CEM Aula feed space. In case of any required changes, you will receive feedback from your tutor. You will need to investigate and read related work such as previous publications on the data or similar data. You need to include a literature review of your findings in your report. Next you have to select, implement and apply appropriate neural network algorithms to the selected problem, performing data pre-processing, if needed, and record the results from the experiments. You can raise any problems encountered in your work in the two follow-up sessions on 17th June 13-15 24th June 13-15 to be held online via MSTeams. Finally, you have to write up your final paper and submit it online by Friday 10th July 18:00. |
|
| Marking criteria | mark |
| 1) Technical quality (rigour of the experiments, data preparation, correct application of the selected algorithms and suitability of the method). 2) You have to provide in appendices evidence of running the experiments. (maintain code and results) |
1) 18% 2) 7% |
This document is for Coventry University students for their own use in completing their
assessed work for this module and should not be passed to third parties or posted on any
website. Any infringements of this rule should be reported to
facultyregistry.eec@coventry.ac.uk.
| 3) Evaluation and discussion of the significance of the results (Why the results are important? 4) How does the paper advance the state of the art? 5) How would the results be useful to other researchers or practitioners? 6) Is this a “real” problem or a small “toy” problem? |
1)10% 2)7% 3)5% 4)3% |
| Social, ethical, legal and professional considerations related to the problem in question. |
5% |
| Clarity of the writing 1) Is there sufficient information for the reader to reproduce the results? 2) References and Presentation (Are results clearly presented, with appropriate visualisations? 3) Is the language used in the paper good? |
1)5% 2)10% 3)15% |
| Originality: 1) Is there some novel approach to the problem, novel use of techniques? 2) Is there any difference from previous contributions? |
1)10% 2)5% |
[Button id=”1″]
[ad_2]
Source link
"96% of our customers have reported a 90% and above score. You might want to place an order with us."
