Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks.
Michelle A. LeeYuke ZhuKrishnan SrinivasanParth ShahSilvio SavareseLi Fei-FeiAnimesh GargJeannette BohgPublished in: CoRR (2018)
Keyphrases
- multiple tasks
- real time
- learning algorithm
- knowledge acquisition
- learning process
- active learning
- data sets
- mobile learning
- learning systems
- computer vision
- real world
- semi supervised
- vision system
- reinforcement learning
- multi modal
- case study
- transfer learning
- incremental learning
- multi task
- learning community
- multi task learning