Distributed training for accelerating metalearning algorithms
Shruti Kunde, Amey Pandit, Mayank Mishra, Rekha Singhal · 2021
The lack of large amounts of training data diminishes the power of deep learning to train models with a high accuracy. Few shot learning (i.e. learning using few data samples) is implemented by Meta-learning, a learn to learn approach. Most gradient based metalearning approaches are hierarchical in nature and computationally expensive. Metalearning approaches generalize well across new tasks by training on very few tasks; but require multiple training iterations which lead to large training times.