The module will focus on deep neural network based learning. This module will introduce you to the fundamentals of deep learning and it will illustrate how it is contributing to the practical design of intelligent machines. Deep learning is currently the most active area of research and development and in high demand for experts by hi-tech start-ups, large companies as well as academia. It is the preferred approach for modern AI and machine learning in any domain. Deep learning techniques enable us to automatically extract features from data so as to solve predictive tasks, such as speech recognition, object recognition, machine translation, question-answering, anomaly detection, medical diagnosis and prognosis, automatic algorithm configuration, personalisation, robot control, time series forecasting, and much more.

Upon successful completion of this module, you will be able to:
1. formulate a deep learning problem
2. discriminate between different practical machine learning problems approaches
3. appraise the merits and shortcomings of model architectures on specific problems
4. Construct and evaluate common neural network models for various types of data
5. Integrate modular components to build deep learning systems in a wide range of real-world applications.
6. Consider appropriate criteria for analysing the results as well as presenting and draw appropriate conclusions

The module includes:
Part 1: Introduction to deep learning
Part 2: Convolutional Neural Networks (CNN)
Part 3: Network Training
Part 4: CNN architectures
Part 5: Recurrent Neural Networks

Part 6: Representation Learning and Autoencoders
Part 7: Generative models
Part 8: Reinforcement Learning I
Part 9: Reinforcement Learning II
Part 10: Hyperparameter optimization