Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale.
Hritik BansalKarthik GopalakrishnanSaket DingliwalSravan BodapatiKatrin KirchhoffDan RothPublished in: CoRR (2022)
Keyphrases
- case study
- learning process
- learning algorithm
- technology enhanced learning
- inductive learning
- multiscale
- learning scheme
- mobile learning
- learning systems
- contextual information
- supervised learning
- image features
- active learning
- prior knowledge
- multi agent systems
- scale space
- knowledge acquisition
- social networks
- background knowledge
- social network analysis
- learning tasks
- learning problems
- artificial intelligence
- bayesian networks
- machine learning