Multimodal machine learning (MMML) is a vibrant multi-disciplinary research field which addresses some of the original goals of artificial intelligence by integrating and modeling multiple communicative modalities, including linguistic, acoustic, and visual messages. With the initial research on audio-visual speech recognition and more recently with language & vision projects such as image and video captioning, this research field brings some unique challenges for multimodal researchers given the heterogeneity of the data and the contingency often found between modalities. This course will teach fundamental mathematical concepts related to MMML including multimodal alignment and fusion, heterogeneous representation learning and multistream temporal modeling. We will also review recent papers describing state-of-the-art probabilistic models and computational algorithms for MMML and discuss the current and upcoming challenges.
The course will present the fundamental mathematical concepts in machine learning and deep learning relevant to the five main challenges in multimodal machine learning: (1) multimodal representation learning, (2) translation & mapping, (3) modality alignment, (4) multimodal fusion and (5) co-learning. These include, but not limited to, multimodal auto-encoder, deep canonical correlation analysis, multi-kernel learning, attention models and multimodal recurrent neural networks. The course will also discuss many of the recent applications of MMML including multimodal affect recognition, image and video captioning and cross-modal multimedia retrieval.
- Time: Tuesdays and Thursday 3:20-4:40 pm
- Content: CMU Canvas
- Location: Remote teaching – Zoom (see links in CMU Canvas)
- Discussion and Q&A: Piazza
- Assignment submissions: Gradescope (for registered students only)
- Online lectures: The lectures will be recorded and made available on CMU Canvas for registered students. External link to the lectures on our Youtube channel!
- Contact: Students should ask all course-related questions on Piazza, where you will also find announcements.
|Aug 24, 2020||Welcome to 11-777, Multimodal Machine Learning, Fall 2020!|