36106 Machine Learning Algorithms and Applications Spring 2024Python

admin管理员组

文章数量:1616433

Java Python SUBJECT OUTLINE

36106 Machine Learning Algorithms and Applications

Spring 2024

Subject description

This subject introduces students to key machine learning algorithms and their application in real-world settings.

Participants are guided in developing an intuitive understanding of how the algorithms work, as well as their strengths   and weaknesses. In addition to gaining practical experience with the algorithms, students develop an understanding of the basic principles of machine learning and the connections between different algorithms. Additionally, they are

exposed to industry standard methodologies for data mining and analytics via readings and assessments. Since data science problems are infused with assumptions, often with ethical and legal implications, due attention is given to

questioning the assumptions behind data and approaches used to analyse it.

Subject learning objectives (SLOs)

Upon successful completion of this subject students should be able to:

1. Apply an industry standard analytics lifecycle methodology for data mining and pattern discovery

2. Interpret, synthesise and communicate insights extracted from machine learning algorithms in a context-appropriate manner.

3. Articulate the strengths, weaknesses and assumptions of a selection of machine learning algorithms in relation to structured and unstructured data

4. Execute and interpret machine learning approaches available for extracting value from data

5. Demonstrate an appreciation, with examples, of a critical, ethical perspective on decisions made throughout the analytics lifecycle

Course intended learning outcomes (CILOs)

This subject also contributes specifically to the development of the following course outcomes:

. Making predictions and informing data discovery

Analyse the value of different models, established assumptions and generalisations, about the behaviour of particular systems, for making predictions and informing data discovery investigations (1.3)

Exploring, interpreting and visualising data

Explore, analyse, manipulate, interpret and visualise data using data science techniques, software and technologies to make sense of data rich environments (2.2)

. Designing and managing data investigations

Apply and assess data science concepts, theories, practices and tools for designing and managing data discovery investigations in professional environments that draw upon diverse data sources, including efforts to shed light on  underrepresented components (2.4)

Developing strategies for innovation

Explore, interrogate, generate, apply, test and evaluate problem-solving strategies to extract economic, business, social, strategic or other value from data (3.1)

Examining and articulating data value

Critically examine the perceived value of data analytics outcomes and clearly articulate implications for different stakeholders and organisations (3.2)

Working together

Develop a collaborative and team-oriented mindset to harness value for stakeholders to produce innovative solutions to challenges (3.3)

Engaging audiences

Explore and craft interpretative narratives that engage key audiences with data analytics and potential significance for action, at a societal, industrial, organisational, group or individual levels (4.2)

· Informing decision making

Develop, test, justify and deliver data project propositions, methodologies, analytics outcomes and

recommendations for informing decision-making, both to specialist and non-specialist audiences (4.3)

Becoming a reflective data practitioner

Engage in active, reflective practice that supports flexible navigation of assumptions, alternatives and uncertainty in professional data science contexts (5.1)

Contribution to the development of graduate attributes

Your experiences as a student in this subject support you to develop the following graduate attributes (GA):

GA 1 Sociotechnical systems thinking

GA 2 Creative, analytical and rigorous sense making GA 3 Create value in problem solving and inquiry

GA 4 Persuasive and robust communication GA 5 Ethical citizenship

Teaching and learning strategies

Blend of online and face to face activities: This subject is offered through a series of block sessions and blends online with face-to-face learning. Students participate in interactive learning experiences in timetabled on-campus  sessions, where they make use of the subject materials that they have already engaged with online. In between

campus sessions, students will engage in individual and collaborative online activities designed to support the understanding of the machine learning algorithms and their application in real-world settings

Collaborative work: A strong emphasis is placed on group activities and interaction, given that graduates of this course will need to approach professional projects and challenges from a collaborative and consensus position.   Insights obtained and developed within the groups is then reworked by individual students to develop the final

summative assessment activity. Group assessments and activities enable students to leverage peer-learning and demonstrate effective skills associated with the topics covered in this subject.

Transdisciplinary approaches: Starting from an elemental perspective on data and data science, students will

approach learning from their specific professional and potential future contexts. As the subject progresses, the students will be able to combine their analytical and technical skills in developing and applying various

machine-learning algorithms, as well as to consider standards and ethical implications of their work.

An aim of this subject is to help you develop academic and professional language and communication skills in order to succeed at university and in the workplace. To determine your current academic language proficiency, one of the assessment tasks in this subject will be used to assess your level of academic English language. If you

receive an unsatisfactory level for English language, you must attend follow up language development activities, in order to pass the su 36106 Machine Learning Algorithms and Applications Spring 2024Python bject. These activities are designed to support you to develop your language and communication skills. Students who do not attend 80% of the language development activities will receive a Fail X grade for the subject.

Assessment task 1: Regression models

Intent: Gain hands-on experience of building regression models using realistic datasets. Objective(s): 1, 2, 3, 4 and 5

Type: Report

Groupwork: Individual Weight: 30%

Task: This assignment is focused on regression modelling.

Please see the assessment brief for details (to be provided in Block Session 2)

Length: Deliverables:

1.  All Python code used to generate the model.

2.  A report articulating an understanding of the problem, the identification and breakdown of tasks   relating to the solution process (as per CRISP-DM) with appropriate visualizations as well as the technical choices made and the reasons for them. In addition to a detailed discussion of the

results, the report should also contain a listing of the key assumptions and their implications.

Due: See weekly program and assessment brief

See also Further information.

Criteria: Both parts of the assignment will be assessed by the following criteria (see assessment brief for

details )

1. Quality, relevance and cleanliness of code and visualisation

2. Quality of scientific experimentation and analytic investigation

3. Depth of discussion of ethics/privacy issues (including matters related to Indigenous people ), value, benefits, risks and recommendation for business stakeholders and final users

4. Strength of justification and explanation for features selected and model used

5. Clarity and quality of written report, data visualisation and appropriateness of communication style to audience

Further information: See weekly program and assessment brief.

To request an extension, students should email the subject coordinator in advance. Typically, we will expect to see appropriate evidence of progress made before granting such extensions.

Assessment task 2: Building and Interpreting a classfication model

Intent: This assignment is focused on classification modelling in detail.

Objective(s): 1, 2, 3, 4 and 5

Type: Report

Groupwork: Individual

Weight: 30%

Length: Deliverables

1.  All Python code used to generate the model.

2.  A comprehensive report articulating an understanding of the problem, the identification and

breakdown of tasks relating to the solution process (as per CRISP-DM) as well as the technical choices made and the reasons for them. In addition to a detailed discussion of the results, the   report should also contain a listing of the key assumptions and their implications. The appendix should list individual contributions to the projects.

Due: See weekly program and assignment brief for details

Criteria: Assignments will be assessed by the following criteria (see assessment brief for details)

1. Quality, relevance and cleanliness of code and visualisation

2. Pertinence and quality of scientific experimentation and analytic investigation

3. Depth of discussion of ethics/privacy issues (including matters related to Indigenous people ), value, benefits, risks and recommendation for business stakeholders and final users

4. Strength of justification and explanation of models selected, data transformation performed, hyperparameters selected and accuracy of results with evidence supporting claims

5. Clarity and quality of written report, data visualisation and appropriateness of communication style to audience

Further To request an extension, students should email the subject coordinator in advance. Typically, we will information: expect to see appropriate evidence of progress made before granting such extensions.

Assessment task 3: End-end Data Science Project

Intent: The intent of this assessment is to help students gain hands-on experience on a real-world project

within a team of data scientists. To this end, students will prepare, process and analyse provided     dataset, interpret results and present insights as a report. They will also reflect on their choices and decisions made on the appropriate solutions to tackle the given problem.

Objective(s): 1, 2, 3, 4 and 5 Type: Report

Groupwork: Group, group and individually assessed Weight: 40%

Length: 1.  All Python code used to generate the model.

2.  A comprehensive report articulating an understanding of the problem, the identification and

breakdown of tasks relating to the solution process (as per CRISP-DM) as well as the technical choices made and the reasons for them. In addition to a detailed discussion of the results, the   report should also contain a listing of the key assumptions and their implications. The appendix should list individual contributions to the projects.

Due: See weekly program and assessment brief for details

See also Further information.

Criteria: Assignments will be assessed by the following criteria (see assessment brief for details)

1. Quality, relevance and cleanliness of code and visualisation

2. Breadth of evidence of collaborative work (e.g. meeting minutes, details of contributions etc)

3. Depth of discussion of ethics/privacy issues (including matters related to Indigenous people ), value, benefits, risks and recommendation for business stakeholders and final users

4. Soundness of justification for selected techniques for a given business problem and objectives

5. Clarity and accuracy of results achieved and supporting evidence provided

6. Clarity and quality of written report, data visualisation and appropriateness of communication style to audience

Further information: See weekly program and assessment brief.

To request an extension, students should email the subject coordinator in advance. Typically, we will expect to see appropriate evidence of progress made before granting such extensions         

本文标签： LearningAlgorithmsmachinePythonApplications