6057CEM Artificial Neural Networks Brief 2023-2024Haskell

Java Python 6057CEM Artificial Neural Networks

Assignment Brief 2023-2024

Very Important 1. File types and method of recording: WORD only 2. Please mention your word count on the first page of your report 3. Submission arrangement: online via Aula (using the submission link in the “Assignments” tab in Aula. No other form. of submission is accepted. 4. Submit before 18:00 04/04/2024 UK Time. Late work will receive a zero mark. 5. File types and method of recording: Submit a WORD file using the “Assignments” link on the 6057CEM AULA Page 6. Mark and Feedback date (DD/MM/YY): 3 weeks after submission (26 April 2024) 7. Mark and Feedback method (e.g. in lecture, electronic via Aula): electronic via Aula 8. The reports that are not in Word format will receive a ZERO mark. The word count does not include the Table of Contents, Code, and Materials in the Appendix. Please place all screenshots, results graphs, and any other images in the Appendix section of the report. Refer to these visuals in the main body of your report.

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 up-to-date libraries to develop solutions to real-world problems and evaluate their performance. 5. Critically evaluate the trends in neural network developments.

Task: In this assignment, you will select one task, such as classification (including object recognition), regression, clustering, forecasting, and recommendation for a problem inspired by the real world and explore how to apply best (deep) neural networks to solve it. The main purpose of this assignment is to: • Test the understanding of fundamental concepts of neural networks and their applications. • Perform. appropriate dataset preparation and evaluate the performance of different neural networks on the chosen dataset. • Gain practical experience using neural network learning algorithms to solve a real-life problem. • Demonstrate the ability to evaluate the results of different learning algorithms critically. Remarks: · You can use any ANN you like, whether it was covered in the module or not. However, · Your work must be strictly related to ANN. No other machine learning methods are accepted. · The dataset you use must be publicly available, e.g., in Kaggle, UCI, or other open repositories: 1. UCI: http://archive.ics.uci.edu/ml 2. Kaggle: https://www.kaggle.com/datasets · Everything you do should be reproducible: The link to the dataset should be provided (direct link to the dataset itself, not the site where it is hosted). The code used, in its totality, should be included as text (not image, file, link, etc.) in the appendix.  If you use a code that is not yours, whether totally or partially, this must be indicated. · You should provide clear evidence in the appendix, using screen captures, that you installed the software and ran every part of the experiments. The screen captures should also clearly show the device (i.e., user ID) on which the experiments were conducted/the software was installed. · Except for the dataset, NO LINKS of any kind to your work are allowed. Everything should be included in the report itself (the body or the appendix) · Plagiarism and collusion are taken extremely seriously. Any part, from any source, of any type, in any language, should be COMPLETELY AND cited. The source should be cited in the caption if you use a figure/table/image that is not yours. Organisation of the report and marking scheme: o Cover page: the project title, Student ID and Word count. o Section 1. Introduction (5 marks) Should include the description of the chosen real-life problem and its significance (1-2 pages) o Section 2. Related work (10 marks) Should explain and properly cite the (most notable) works already done related to the selected problem. The references need to be from journal papers, not just from websites. o Section 3. Dataset (10 marks) Include the description of the publicly available dataset and its link (1-3 pages). Please describe the processes you use to clean and formalize the data set for your use.  Section 4. Method(s) (15 marks) Should describe the appropriate neural network(s), the learning algorithm(s), and other parameters tried to solve the problem. Please provide the reasoning behind selecting the type of the neural network and parameters. o Section 5. Experimental results (15 marks) Should explain the rigor experiments conducted and compare their detailed results. o Section 6. Discussion and future work (5 marks) Should present the summary of the findings (1-2 pages). Also provide what future work can be conducted on this project. o References (5 marks) List of references cited in the other sections, in the APA style. o Appendix 1- Screenshots and steps (10 marks) Should contain the screenshots of all the steps together with brief descriptions such that an interested reader can re-do all the experiments in this research. o Implementing a Neural Network model form. the scratch. (5 Marks) o Appendix 2- Code (10 marks) The complete code in text (in readable format) The remaining 10 marks is for the overall presentation of the report (e.g., its organization, format, and clarity). Please use a short yet meaningful title in the cover page. You should use the existing journal papers in the literature as examples to better realise what to include in each section. Please start each section on a new page for more readable.

Notes: 1. You are expected to use Coventry University APA style. for referencing. For support and advice on this students can contact Centre for Academic Writing (CAW). 2. Please notify your registry course support team and module leader for disability support. 3. Any student requiring an extension or deferral should follow the university process as outlined here. 4. 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. 5. If there are technical or performance issues that prevent 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 your Module Leader. 6. Assignments that are more than 10% over the word limit will result in a deduction of 10% of the mark i.e. a mark of 60% will lead to a reduction of 6% to 54%. The word limit includes quotations, but excludes the bibliography, reference list and tables. 7. You are encouraged to check the originality of your work by using the draft Turnitin links on Aula. 8. 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. This applies to both coursework and exam answers. 9. A marked difference between your writing style, knowledge and skill level demonstrated in class discussion, any test conditions and that demonstrated in a coursework assignment may result in you having to undertake a Viva Voce to prove the coursework assignment is entirely your own work. 10. If you make use of the services of a proofreader in your work, you must keep your original version and make it available as a demonstration of your written efforts.  Also, please read the university Proof Reading Policy. 11. 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, with the exception of resits, where for the coursework, you may be asked to rework and improve a previous attempt.   This requirement will be specifically detailed in your assignment brief or specific course or module information. Where earlier work by you is citable, i.e., it has already been published/submitted, you must reference it clearly.  Identical pieces of work submitted concurrently may also be considered to be self-plagiarism.

General Marking Rubric

Mark band	Outcome	Guidelines
90-100%   Distinction	Meets learning outcomes	Distinction - Exceptional work with very high degree of rigour, creativity and critical/analytic skills.  Mastery of knowledge and subject-specific theories with originality and autonomy. Demonstrates exceptional ability to analyse and apply concepts within the complexities and uncertainties of the subject/discipline. Innovative research with exceptional ability in the utilisation of research methodologies.  Demonstrates, creativity, originality and outstanding problem-solving skills.  Work completed with very high degree of accuracy, proficiency and autonomy.  Exceptional communication and expression demonstrated throughout. Student evidences the full range of technical and/or artistic skills. Work pushes the boundaries of the discipline and may be strongly considered for external publication/dissemination/presentation.
80-89%   Distinction		Distinction - Outstanding work with high degree of rigour, creativity and critical/analytic skills.  Near mastery of knowledge and subject-specific theories with originality and autonomy. Demonstrates outstanding ability to analyse and apply concepts within the complexities and uncertainties of the subject/discipline. Innovative research with outstanding ability in the utilisation of research methodologies.  Work consistently demonstrates creativity, originality and outstanding problem-solving skills.  Work completed with high degree of accuracy, proficiency and autonomy.  Outstanding communication and expression demonstrated throughout. Student demonstrates a very wide range of technical and/or artistic skills. With some amendments, the work may be considered for external publication/dissemination/presentation
70-79%   Distinction		Distinction - Excellent work undertaken with rigour, creativity and critical/analytic skills.  Excellent degree of knowledge and subject-specific theories with originality and autonomy demonstrated. The work exhibits excellent ability to analyse and apply concepts within the complexities and uncertainties of the subject/discipline. Innovative research with excellent ability in the utilisation of research methodologies.  Work demonstrates creativity, originality and excellent problem-solving skills.  Work completed with very consistent levels of accuracy, proficiency and autonomy.  Excellent communication and expression demonstrated throughout. Student demonstrates a very wide range of technical and/or artistic skills.
60-69%   Merit		Merit - Very good work often undertaken with rigour, creativity and critical/analytic skills.  Very good degree of knowledge and subject-specific theories with some originality and autonomy demonstrated. The work often exhibits the ability to fully analyse and apply concepts within the complexities and uncertainties of the subject/discipline. Very good research evidence and shows very good ability in the utilisation of research methodologies.  Work demonstrates creativity, originality and problem-solving skills.  Work completed with very consistent levels of accuracy, proficiency and autonomy.  Very good communication and expression demonstrated throughout. Student demonstrates a wide range of technical and/or artistic skills.
50-59%   Pass		Pass - Good work undertaken with some creativity and critical/analytic skills.   Demonstrates knowledge and subject-specific theories with some originality and autonomy demonstrated. The work exhibits the ability to analyse and apply concepts within the complexities and uncertainties of the subject/discipline. Good research and shows some ability in the utilisation of research methodologies.  Work demonstrates problem-solving skills and is completed with some level of accuracy, proficiency and autonomy.  Satisfactory communication and expression demonstrated throughout. Student demonstrates some of the technical and/or artistic skills.
40-49%   Pass		Pass - Assessment demonstrates some advanced knowledge and understanding of the subject informed by current practice, scholarship and research. Work may be incomplete with some irrelevant material present. Sometimes demonstrates the ability to analyse and apply concepts within the complexities and uncertainties of the subject/discipline. Acceptable research with evidence of basic ability in the utilisation of research methodologies.  Demonstrates some originality, creativity and problem-solving skills but often with inconsistencies.  Expression and presentation sufficient for accuracy and proficiency.  Sufficient communication and expression with professional skill set.  Student demonstrates some technical and/or artistic skills.
30-39%   Fail	Fails to achieve learning outcomes	Fail - Very limited understanding of relevant theories, concepts and issues with deficiencies in rigour and analysis. Some relevant material may be present but be informed from very limited sources. Fundamental errors and some misunderstanding likely to be present. Demonstrates limited ability to analyse and apply concepts within the complexities and uncertainties of the subject/discipline. Limited research scope and ability in the utilisation of research methodologies.  Limited originality, creativity, and struggles with problem-solving skills.  Expression and presentation insufficient for accuracy and proficiency.  Insufficient communication and expression and with deficiencies in professional skill set.  Student demonstrates deficiencies in the range of technical and/or artistic skills.
20-29%   Fail -		Fail - Clear failure demonstrating little understanding of relevant theories, concepts, issues and only a vague knowledge of the area. Little relevant material may be present and informed from very limited sources. Serious and fundamental errors and virtually no evidence of relevant research.  Fundamental errors and misunderstandings likely to be present. Little or no research with no evidence of utilisation of research methodologies.  No originality, creativity, and struggles with problem-solving skills.  Expression and presentation insufficient for accuracy and proficiency.  Insufficient communication and expression and with serious deficiencies in professional skill set.  Student has clear deficiencies in range of technical and/or artistic skills.
0-19%   Fail		Fail - Clear failure demonstrating no understanding of relevant theories, concepts, issues and no understanding of area. Little or no relevant material may be present and informed from minimal sources.  No evidence of ability in the utilisation of research methodologies. No evidence of originality, creativity, and problem-solving skills.  Expression and presentation deficient for accuracy and proficiency.  Insufficient communication and expression and with deficiencies in professional skill set.  Student has clear deficiencies in range of technical and/or artistic skills