A. Knowledge and understanding
At the end of the module, learners will be expected to:
A1: Understand the context of Artificial Intelligence, Machine Learning and deep learning, including understanding the basic mechanisms and appropriate uses of a range of alternatives to deep learning.
A2: Describe the range of situations in which machine learning systems are used and the possibilities and limitations of these systems.
A3: Understand the key elements and mechanisms of deep neural learning systems, together with their strengths and weaknesses.
A4: Understand the social, professional, legal, and ethical issues associated with machine learning systems.
B. Cognitive skills
At the end of the module learners will be expected to:
B1: Explain the strengths, weaknesses, and limitations of machine learning, and deep learning in particular, including understanding when machine learning techniques are not appropriate.
B2: Apply and critically evaluate deep learning tools and techniques to solve real-world problems.
B3: Select and apply appropriate techniques and tools for designing, implementing, and testing deep learning systems, and be aware of their limitations.
B4: Justify why deep learning tools and
techniques are either suitable or not for a particular problem or domain
C. Practical and professional skills
At the end of the module, learners will be expected to:
C1: Analyse and evaluate problems and plan strategies for their solution.
C2: Select an appropriate set of machine learning techniques for a given task and dataset, marshal one or more tools into a coherent machine learning system, apply the machine learning system correctly, and evaluate its performance (including limits of applicability).
C3: Select and appropriately pre-process a dataset for machine learning and evaluate how biases inherent in the data will affect the reliability and fairness of the trained machine learning system.
D Key transferable skills
At the end of the module, learners will be expected to:
D1: Relate the strengths, weaknesses, and limitations of machine learning to wider social issues, including social justice, privacy and security, and access to resources and services.
D2: Communicate information, arguments, ideas, and issues clearly and in appropriate ways, considering the audience and purpose of the communication.
D3: Select and use accurately analytical techniques to solve problems.
D4: Develop skills to become an independent lifelong learner, as the field moves on.