Content deleted Content added
Citation bot (talk | contribs) Alter: template type. Add: journal, authors 1-1. Removed parameters. Some additions/deletions were parameter name changes. | Use this bot. Report bugs. | Suggested by AManWithNoPlan | #UCB_webform 173/1682 |
Thatsme314 (talk | contribs) m →Common approaches: improve citation formatting |
||
Line 39:
====Meta Networks====
Meta Networks (MetaNet) learns a meta-level knowledge across tasks and shifts its inductive biases via fast parameterization for rapid generalization.<ref name="paper3">[https://arxiv.org/abs/1703.00837] Tsendsuren Munkhdalai
===Metric-Based===
Line 45:
====Convolutional Siamese [[Neural Network]]====
Siamese [[neural network]] is composed of two twin networks whose output is jointly trained. There is a function above to learn the relationship between input data sample pairs. The two networks are the same, sharing the same weight and network parameters.<ref name="paper4">[http://www.cs.toronto.edu/~rsalakhu/papers/oneshot1.pdf] Gregory Koch
====Matching Networks====
Matching Networks learn a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types.<ref name="paper5">[http://papers.nips.cc/paper/6385-matching-networks-for-one-shot-learning.pdf] Vinyals, O.
====Relation Network====
The Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to learn a deep distance metric to compare a small number of images within episodes, each of which is designed to simulate the few-shot setting.<ref name="paper6">[http://openaccess.thecvf.com/content_cvpr_2018/papers_backup/Sung_Learning_to_Compare_CVPR_2018_paper.pdf] Sung, F.
====Prototypical Networks====
Prototypical Networks learn a [[metric space]] in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve satisfied results.<ref name="paper7">[http://papers.nips.cc/paper/6996-prototypical-networks-for-few-shot-learning.pdf] Snell, J.
===Optimization-Based===
Line 60:
====LSTM Meta-Learner====
LSTM-based meta-learner is to learn the exact [[optimization algorithm]] used to train another learner [[neural network]] [[classification rule|classifier]] in the few-shot regime. The parametrization allows it to learn appropriate parameter updates specifically for the [[scenario]] where a set amount of updates will be made, while also learning a general initialization of the learner (classifier) network that allows for quick convergence of training.<ref name="paper8">[https://openreview.net/pdf?id=rJY0-Kcll] Sachin
====Temporal Discreteness====
MAML, short for Model-Agnostic Meta-Learning, is a fairly general [[optimization algorithm]], compatible with any model that learns through gradient descent.<ref name="paper9">[https://arxiv.org/abs/1703.03400] Chelsea Finn, Pieter Abbeel, Sergey Levine (2017). “Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks” arXiv:1703.03400 [cs.LG]</ref>
====Reptile====
Reptile is a remarkably simple meta-learning optimization algorithm, given that both of its components rely on [[meta-optimization]]] through gradient descent and both are model-agnostic.<ref name="paper10">[https://arxiv.org/abs/1803.02999]
==Examples==
| |||