Meta-neural networks that learn by learning

By Devang Naik, Richard James Mammone. 1992

How researchers see this paper

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

In Model Architectures

Citations in the corpus

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 learn by gradient descent by gradient descent (2016, background): “In some of the earliest work on meta-learning, Naik and Mammone [1992] use the results from previous training runs to modify the descent direction of backpropagation; however, their update strategy is somewhat more ad-hoc and not directly learned.”
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.”
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].”
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.”
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].”
Recasting Gradient-Based Meta-Learning as Hierarchical Bayes (2018, background): “This capacity for meta-learning also has the potential to enable an artiﬁcially intelligent agent to learn more efﬁciently in situations with little available data or limited computational resources (Schmidhuber, 1987; Bengio et al., 1991; Naik & Mammone, 1992).”
Meta-learning autoencoders for few-shot prediction (2018, background): “MeLA addresses the problem of meta-learning [22, 19, 16], where an important subﬁeld is to quickly adapt to new tasks with one-shot or few-shot examples.”
Incremental Meta-Learning via Indirect Discriminant Alignment (2020, neutral): “Meta-learning [36, 22, 31] for few-shot learning [24, 6, 30, 38, 35, 19, 25, 10] uses a relatively “meta training” dataset from which several few-shot tasks are sampled to mimic phenomena at the tail.”
Learning to Learn for Global Optimization of Black Box Functions (2016, methodology): “The idea of applying machine learning techniques to optimize the process of learning itself has a long history [Schmidhuber, 1987, Naik and Mammone, 1992, Thrun and Pratt, 1998].”
Incremental Few-Shot Learning with Attention Attractor Networks (2018, background): “First proposed in Schmidhuber (1987); Naik & Mammone (1992); Thrun (1998), meta-learning is a machine learning paradigm where the meta-learner tries to improve the base learner using the learning experiences from multiple tasks.”
Meta-Transfer Learning for Few-Shot Learning (2018, neutral): “In contrast to data-augmentation methods, meta-learning is a task-level learning method [2, 32, 51].”
Learned Optimizers that Scale and Generalize (2017, background): “There are many works related to this idea, including (Sutton, 1992; Naik & Mammone, 1992; Thrun & Pratt, 1998; Hochreiter et al., 2001; Santoro et al., 2016).”
Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL (2018, methodology): “Our approach builds on techniques for meta-learning or learning-to-learn (Thrun & Pratt, 1998; Schmidhuber, 1987; Bengio et al., 1992; Naik & Mammone, 1992).”
Online Meta-Learning (2019, positive): “Our work proposes to use meta-learning or learning to learn (Thrun & Pratt, 1998; Schmidhuber, 1987; Naik & Mammone, 1992), in the context of online (regret-based) learning.”
Meta-Learning Improves Lifelong Relation Extraction (2019, background): “Meta-Learning Meta-learning, or learning to learn (Schmidhuber, 1987; Naik and Mammone, 1992; Thrun and Pratt, 1998), aims to develop algorithms that learn a generic knowledge of how to solve tasks from a given distribution of tasks, by generalizing from solving related tasks from that distribution.”
Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning (2018, background): “Our problem setting relates to meta-learning, a long-standing problem of interest in machine learning that is concerned with enabling artificial agents to efficiently learn new tasks by learning to learn (Thrun and Pratt, 1998; Schmidhuber and Huber, 1991; Naik and Mammone, 1992; Lake et al., 2015).”