Sponsor:
Meta-learning focuses on learning over the task space rather than instance space by training a general model which is able to quickly adapt to new unseen tasks. The implications of fast adaptation to new unseen tasks can also be effective on the traditional paradigm of neural networks training. Modeling generalization, few-shot learning, and task generation are studied in this project.Related work:
- A. E. Eshratifar, D. Eigen, M. Pedram, Gradient Agreement as an Optimization Objective for Meta-learning, NeurIPS meta-learning workshop, Dec. 2018.
- E. Eshratifar, M. S. Abrishami, D. Eigen, M. Pedram, A Meta-learning Approach for Custom Model Training, AAAI, Jan. 2019