Lecture 4.1 - Multimodal Alignment (CMU Multimodal Machine Learning, Fall 2023)

Lecture 4.1 - Multimodal Alignment (CMU Multimodal Machine Learning, Fall 2023)
Topics: explicit alignment, multimodal training, multimodal grounding
----------------------------------------------------------------------------------------------------------------
Carnegie Mellon University, 11-777 Multimodal Machine Learning, 2023 Fall
Website: cmu-multicomp-...
Instructor: Louis-Philippe Morency
Co-lecturer: Paul Liang
This revised version of CMU Multimodal Machine Learning course presents the fundamental mathematical concepts in machine learning and deep learning relevant to the six main challenges in multimodal research: (1) representation, (2) alignment, (3) reasoning, (4) generation, (5) transference and (6) quantification. This revised course is based on the new taxonomy introduced in this survey paper: arxiv.org/abs/...