This module equips students with a strong foundation in deep learning concepts and their applications in visual intelligence. Learners will explore neural network architectures, computation processes, optimisation techniques, and model evaluation strategies. The module introduces core computer vision tasks such as image and video analysis, emphasising the use of convolutional neural networks (CNNs) to address real-world challenges. Students will gain hands-on experience in developing and deploying models for object classification, detection, segmentation, and pose estimation. The module also explores generative models and emerging trends in visual AI, examining industry applications that illustrate how these technologies are transforming multiple sectors.