EESC6368 - Multimodal Deep Learning

EESC 6368 (CE 6368) Multimodal Deep Learning (3 semester credit hours) Theory and applications in the field of multimodal deep learning. Robustness and performance of systems by considering cross-modal integration. Deep learning methods used for representation, translation, alignment, fusion, and co-learning of multimodal content. Multimodal embeddings and their applications. Use of deep learning solutions such as convolutional neural network (CNN), Long short-term memory (LSTM), and attention models to process multimodal data. Recommended Corequisite: EESC 6349. Prerequisite: ENGR 3341 or equivalent. (3-0) T