Deep learning is applicable to a wide range of modern data science and artificial intelligence problems, such as image classification, speech recognition, and text classification. Deep Learning I is an introductory module that covers the fundamental concepts and techniques of deep learning. It serves as a foundation for more advanced topics in deep learning. Topics include: (1) Introduction to Neural Networks: Understanding the basic structure and functioning of artificial neural networks; (2) Activation Functions: Exploring different activation functions used in neural networks and their impact; (3) Backpropagation: Learning how neural networks are trained using backpropagation; (4) Convolutional Neural Networks (CNNs): Introduction to CNNs and their applications in computer vision; (5) Recurrent Neural Networks (RNNs): Understanding RNNs and their use in sequential data analysis; (6) Deep Learning Frameworks: Hands-on experience with popular deep learning libraries like TensorFlow or PyTorch; (7) Practical Applications: Exploring real-world use cases of deep learning in various fields.
Learning Outcomes
By the end of the module students should be able to:
Understand the basics of neural networks and their building blocks.
Acquire knowledge of key deep learning architectures like CNNs and RNNs.
Gain proficiency in implementing and training neural networks using common deep learning libraries.
Apply deep learning techniques to solve real-world data science problems.
Assessment
Assessment Methods & Exceptions
Assessment:
1.5 hours 80% examination, 20% coursework problem sheets.
