Course overview
The course aims to provide students with a comprehensive understanding of fundamental concepts in neural networks and deep learning with practical skills in model training, development, and validation. Building on prior knowledge of machine learning and its mathematical foundation, students will learn about various types of neural network architectures and deep learning. They will gain hands-on experience in programming deep learning systems using Python. By the end of the course, students will be proficient in designing, training, and evaluating deep learning models for various tasks, including classification, regression, and generative modelling on real-world datasets. This course provides students with the necessary skills and knowledge required by modern machine learning professionals and a solid foundation for further life-long learning in machine learning.
Course learning outcomes
- Select a suitable neural network architecture for a given problem
- Implement neural network architectures in a modern framework
- Apply the machine learning pipeline to neural network models on complex datasets
- Evaluate different deep learning architectures for specific tasks
- Apply deep learning models for natural language processing and computer vision
- Present results and recommendations to stakeholders