ACS341 Machine Learning

Module Description (subject to change)

Machine learning is a component of artificial intelligence that enables a computer to learn how to perform a task from data or simulations rather than being explicitly programmed for every possible scenario. Machine learning is currently being applied in a number of fields including finance, robotics and autonomous systems and bioinformatics and has experienced a huge growth in industry in recent years. This module introduces the key foundational elements of machine learning, including: regression, classification and reinforcement learning. The module is taught by a combination of lectures and labs, where there is an emphasis on practical implementation of different methods.

Credits: 10 (Spring Semester)

Pre-requisites: ACS234

Module Leader

John O 125x125







Dr John Oyekan
Email: j.oyekan@sheffield.ac.uk
Amy Johnson Building

If you have any questions about the module please talk to us during the lectures or the labs in the first instance. It is likely that other students will learn from any questions you ask as well, so don’t be afraid to ask questions.

Outside of lectures please contact me via email, or drop in to see me.

Learning Outcomes

Learning Outcomes

By the end of the module students will be able to:

  • The student should be able to comprehend and articulate the motivation, ethical issues and future challenges in machine learning and AI technologies [SM1p, SM6m, ET1m, EP4m]
  • The student should be able to analyse a particular problem and select the appropriate machine learning methodology to apply [SM2p, EA3m]
  • The student should be able to design and construct machine learning systems while taking into consideration how they interact with external systems [EA1p, D4p]
  • The student should comprehend and explain the motivation of different machine learning methodologies and be able to explain their strengths and weaknesses [EP2p]
This module satisfies the AHEP3 (Accreditation of Higher Education Programmes, Third Edition) Learning Outcomes that are listed in brackets after each learning outcome above. For further details on AHEP3 Learning Outcomes, see the downloads section of our accreditation webpage.
Syllabus

Syllabus

This module covers both machine learning methodologies as well as techniques on how to build effective machine learning environments.

This module will cover:
  • Overview of Machine Learning
  • Challenges in Machine Learning
  • Developing Machine Learning pipelines
  • Decision Trees
  • Regression
  • Dimension reduction and visualisation techniques
  • Clustering
  • Support Vector Machines
  • Teaching Methods

Learning and Teaching Methods

NOTE: This summary of teaching methods is representative of a normal Semester. Owing to the ongoing disruption from Covid-19, the exact method of delivery will be different in 2020/21.

  • Lectures: 10 hours
  • Labs: 20 hours
  • Independent Study: 68 hours
  • Teaching Materials

Learning and Teaching Materials

  • All teaching materials will be available via Blackboard (MOLE).
  • Assessment

Assessment

  • Lab Exercise (15%)
  • Assignment (25%)
  • Group Project (60%)
  • Feedback

Feedback

  • This module has regular lectures where students are encouraged to ask questions as needed. The laboratory sessions will allow students to ask for feedback on their progress and raise any other concerns as well as seek more detailed feedback and assistance.
  • Students will receive individual feedback on their lab work with worked solutions and individual feedback on assignment 2 in the form of solution evaluations.
  • Student Evaluation

Student Evaluation

  • Students are encouraged to provide feedback during the module direct to the lecturer. Students will also have the opportunity to provide formal feedback via the Faculty of Engineering Student Evaluation Survey at the end of the module.
  • You can view the latest Department response to the survey feedback here.
  • Recommended Reading

Recommended Reading

  • Hands-on Machine Learning with Scikit-Learn and TensorFlow (Aurelien Geron)