Deep Learning and Applications
About This Course
This course equips learners with a deep understanding of modern neural network architectures, including Convolutional Neural Networks (CNNs), Residual Networks, and Transformer Networks, while exploring the design principles behind them. Learners will learn to design and refine advanced deep learning techniques, evaluate performance using rigorous research-based metrics, and apply mathematical analysis to interpret network behaviour. The course emphasises practical skills in hyperparameter tuning and heuristic optimisation for achieving optimal performance. By the end of the course, learners will be prepared to build, analyse, and optimise cutting edge neural architectures for real world applications in AI and machine learning.
What You'll Learn
1. Describe concretely modern neural network architectures including Convolutional Neural Networks (CNNs) and Transformer Networks and discuss design rationales.
2. Design and refine existing deep learning techniques and neural architectures and evaluate their performance.
3. Apply mathematical analysis and heuristics techniques to interpret neural networks behaviour and systematically tune hyperparameters for optimal performance.
Entry Requirements
No pre-requisites are needed to enroll in the individual courses; however, learners without qualifications or work experience in relevant engineering or the related fields may find the course contents challenging. Prior knowledge in STEM field will be an advantage.