Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

2017

Subfields: Meta & Continual Learning

Citations in the corpus

• Set Transformer (2018, neutral): “For example, few-shot image clas-sification (Finn et al., 2017; Snell et al., 2017; Lee & Choi, 2018) operates by building a classifier using a support set of images, which is evaluated with query images.”
• Online Meta-Learning (2019, neutral): “Meta-learning (Schmidhuber, 1987; Vinyals et al., 2016; Finn et al., 2017) casts this as the problem of learning to learn, where past experience is used to acquire a prior over model parameters or a learning procedure, and typically studies a setting where a set of meta-training tasks are made avail”
• Challenges of Real-World Reinforcement Learning (2019, neutral): “System identification involves training a policy that can determine online the environment in which it is operating and modify the policy accordingly (Finn et al., 2017; Nagabandi et al., 2018).”
• Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning (2018, background): “(3)Our partial ranking of few-shot learning methods based on target-domain accuracy is: [27] > [9, 30] > [23] > [7] > [11] > [32] > [13].”