ml:meta-learning

This is an old revision of the document!

Table of Contents

Meta-Learning

Meta-Learning

Overviews

Hospedales et al 2020 - Meta-Learning in Neural Networks: A Survey

AutoML

Deep Learning Papers

Hochreiter & Younger 2001 - Learning to Learn Using Gradient Descent Amazing paper from one of the inventors of LSTMs. Jeurgen talks about it here.
Andrychowicz et al 2016 - Learning to Learn by Gradient Descent by Gradient Descent
Ha et al 2016 - HyperNetworks
Chen 2017 - Learning to Learn without Gradient Descent by Gradient Descent Learns a black-box optimizer (gradient-free optimizer). Can be applied to hyperparameter tuning.
Kirsch & Schmidhuber 2021 - Meta Learning Backpropagation And Improving It
Zhmoginov et al 2022 - HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning (interview)

Non-Deep Learning Papers

Meta-Learning in NLP

Bansal et al 2019 - Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks
https://arxiv.org/pdf/2111.01322.pdf|Bansal et al 2021 - Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP]]

Related Pages

Neural Architecture Search

ml/meta-learning.1646348647.txt.gz · Last modified: 2023/06/15 07:36 (external edit)