Learning how to learn

By Kyle Duffie. 2019

2,217 citations recorded by the source corpus.

Subfields: Education, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Education

In Reinforcement Learning

Citations in the corpus

Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions (2017, background): “Learning to learn or meta-learning has been studied in cognitive science and machine learning for decades (Harlow, 1949; Thrun & Pratt, 1998; Hochreiter et al., 2001).”
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (2017, methodology): “The method that we propose in this paper addresses the general problem of meta-learning (Thrun & Pratt, 1998; Schmidhuber, 1987; Naik & Mammone, 1992), which includes few-shot learning.”
Learning to Optimize Neural Nets (2017, background): “More broadly related is work on “meta-learning” and “learning to learn” (Baxter et al., 1995; Vilalta & Drissi, 2002; Brazdil et al., 2008; Thrun & Pratt, 2012).”
Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges (2019, background): “On the other hand, one-to-many multilingual NMT can be considered a multi-task problem (Caruana, 1997; Thrun and Pratt, 1998; Dong et al., 2015), where each source-target pair is a separate task.”
Parameter-Efficient Transfer Learning for NLP (2019, background): “Continual Learning As an alternative to simultaneous training, continual, or lifelong, learning algorithms aim to learn from a sequence of tasks (Thrun, 1998).”
One-Shot Imitation Learning (2017, methodology): “Like our algorithm, many of the aforementioned approaches are a form of meta-learning (Thrun & Pratt, 1998; Schmidhuber, 1987; Naik & Mammone, 1992), where the algorithm itself is being learned.”
Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning (2020, methodology): “We also analyse the trade-off be-tween freezing or not freezing the language model parameters by leveraging two learning settings, multi-task (MT) (Caruana, 1997) and continual learning (CL) (Thrun and Pratt, 2012).”
ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition (2021, background): “Meta-learning algorithms which “learn to learn” [45, 9, 49, 11] hold partic(a) Frames from clean videos”
CrossTransformers: spatially-aware few-shot transfer (2020, background): “Few-shot learning [25, 35, 46, 53] has recently been primarily addressed in the meta-learning framework [57, 71, 80], where a model learns an update rule for the parameters of a base-learner model [6, 7, 72] through a sequence of training episodes [79, 88].”
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes (2019, methodology): “This general approach relates to methods for meta-learning [1, 2] and few-shot learning [3].”
Meta-Learning Probabilistic Inference for Prediction (2018, positive): “Second, we share information between tasks about how to learn and perform inference using meta-learning (Naik and Mammone, 1992; Thrun and Pratt, 2012; Schmidhuber, 1987).”
Meta-learning with differentiable closed-form solvers (2018, background): “learning to learn) [14, 15, 29] has been of great importance in the Machine Learning community for several decades.”
Neural Architecture Search with Reinforcement Learning (2016, background): “Also related to our work is the idea of learning to learn or meta-learning (Thrun & Pratt, 2012), a general framework of using information learned in one task to improve a future task.”
Adaptive Gradient-Based Meta-Learning Methods (2019, background): “In contrast, the ARUBA framework can handle general classes of meta-algorithms, which leads not only to new and improved results in static, dynamic, and statistical settings but also to signiﬁcantly more practical LTL methods.”
Metrics for Explainable AI: Challenges and Prospects (2018, methodology): “epts and relations (including causal connections or state transitions) has been noted in education as a method for comparing the mental models of students to those of experts or their instructor (see Novak and Gowin, 1984); noted in social studies as a method for comparing individuals' mental m”
Meta-Gradient Reinforcement Learning (2018, background): “Among the earliest studies on meta learning (or learning to learn [Thrun and Pratt, 1998]), Schmidhuber [1987] applied genetic programming to itself to evolve better genetic programming algorithms.”
Task Agnostic Meta-Learning for Few-Shot Learning (2018, background): “The idea of meta-learning has been proposed more than a couple of decades ago [3, 4, 5].”
Meta-SGD: Learning to Learn Quickly for Few Shot Learning (2017, background): “and its huge potential in practice [23].”
Learning to Optimize (2016, background): “This line of work, known as “learning to learn” or “meta-learning” [1, 27, 5, 26], considers the problem of devising methods that can take advantage of knowledge learned on other related tasks to train faster, a problem that is today better known as multi-task learning and transfer learning.”
Recasting Gradient-Based Meta-Learning as Hierarchical Bayes (2018, background): “In machine learning, meta-learning is formulated as the extraction of domain-general information that can act as an inductive bias to improve learning efﬁciency in novel tasks (Caruana, 1998; Thrun & Pratt, 1998).”