Deep Learning and Explainable AI

Introduction

Deep learning models have achieved state-of-the-art performance in tasks such as image classification, representation learning, and data generation. This course explores various deep learning architectures, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and autoencoders; as well as probabilistic graphical models and variational autoencoders (VAEs). Students will gain hands-on experience in implementing and training deep learning models using TensorFlow.

Additionally, as interpretability of the results is crucial in many real-world applications, the course introduces principles and techniques of Explainable Artificial Intelligence (XAI), equipping students with the skills to make deep learning models more transparent and interpretable.

Course content

To address the learning outcomes listed above, the course content covers the following topics:

·       Introduction to deep learning - history, positioning in AI, applications, and recent developments and challenges

·       Feedforward neural networks – backpropagation and gradient descent

·       Image processing with CNNs

·       Sequential data modelling with RNNs and Transformers

·       Representation learning with Autoencoders

·       Generative modelling with VAEs and probabilistic graphical models

·       General principles and a choice of techniques of Explainable AI