This is Block 16 (15 ECTS) on the 3+1 Integrated BSc/MSc Immersive Software Engineering and is the second block of the MSc track. It runs in the autumn semester Weeks -1 to 7 (8 Weeks) and is classified as 2 1 in SITS. Students will learn to design solutions leveraging multi-modal intelligent paradigms for a variety of problems ranging from games to smart cities to automatic programming. Students will acquire the knowledge and techniques necessary to effectively formulate a hypothesis, capture and clean data where relevant, and apply artificial intelligence and machine learning architectures to the problem at hand. Students will critically evaluate the applied paradigms, and develop competency in quantitative and qualitative critical thinking.

1. Defining intelligence and learning: the Turing test, Pearle's Chinese room, 2. History of AI 3. The ethical dilemmas associated with artificial intelligence and machine learning 4. Evaluating paradigms: false positives, false negatives, precision and recall, confusion matrix, Area Under the Curve (AUC), 5. Evolutionary Algorithms (EAs): an analysis of the core concepts based on neoDarwinian principles of survival of the fittest and natural selection, the variants ranging from Genetic Algorithms to Genetic Programming to Grammatical Evolution, and their application to optimisation and synthesis such as evolutionary robotics and automatic programming. 6. Reinforcement Learning: Bellman's equation, Dynamic Programming, Monte Carlo methods, Temporal Difference methods with eligibility traces, policy gradient methods, applied to games and other domains. 7. Monte Carlo Tree Search 8. Artificial Neural Networks: the perceptron, Multi-Layered Perceptron (MLP) and Back Propagation (BP), Recurrent networks, Self Organising Maps (SOMs), applied to domains such as financial prediction, face detection and classification, and document retrieval. 9. Causal Networks and Bayesian Belief 10. Robotics: Sense-Plan-Act (SPA) cycle, subsumption architecture, autonomous and intelligent control, marine robotics, unmanned aerial vehicles, humanoid robotics. 11. Deep Learning - An overview of deep neural network architectures such as Convolutional Neural Networks, Recurrent Neural Networks, Long-Short-Term Memory models, Recursive Neural Networks, Generative Adversarial Networks applied to a variety of problems from computer vision to FinTech to the arts and natural language processing. 12. Deep learning workflow on deep learning frameworks using a selection from Keras, TensorFlow, PyTorch, Caffe2, and MatLab.

On successful completion of this module, students will be able to: - Differentiate between deep learning, machine learning, and artificial intelligence - Formulate a research question that necessitates the use of paradigms from the field of artificial intelligence and machine learning - Select an appropriate learning paradigm from a range of alternatives, and then apply it to a given real-world problem. - Apply deep learning techniques to a subset of problems in control and classification - Source and clean datasets where available and necessary for the solution. - Interpret and evaluate the outputs of an artificial intelligence and machine learning architecture. - Use techniques such as confusion matrices and area under the curve to evaluate artificial intelligence and machine learning models - Use the Sense-Plan-Act cycle to design intelligent, autonomous robotics systems - Demonstrate competency in the use of learning frameworks such as TensorFlow etc. on a cloud hosted platform.

On successful completion of this module, students will be able to: - Given problems and data to investigate, the student will identify and discuss any significant ethical issues such as privacy, confidentiality, ownership, transparency and identity. - Given datasets, the student will question and demonstrate whether the data is representative and identify potential biases. - Following exposure to various frameworks and hosted platforms, the student will judge and challenge the limitations of current deep learning techniques.

On successful completion of this module, students will be able to:

The block is taught using the problem-based learning, the flipped classroom concept, and blended learning in a state of the art laboratory setting with an emphasis on collaborative practice and technical excellence. Learning and teaching will be research led with a focus on translating theory into practice, innovation and knowledge creation.