Fast learning for problem classes using knowledge based network initialization

24 citations recorded by the source corpus.

How researchers see this paper

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

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (2017, background): “Most of these works have considered good random initial-izations, though a number of papers have addressed data-dependent initializers (Kr¨ahenb¨uhl et al., 2016; Salimans & Kingma, 2016), including learned initializations (Husken & Goerick, 2000; Maclaurin et al., 2015).”
Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm (2017, methodology): “In contrast to the aforementioned approaches, more recent work has proposed methods that include the structure of optimization problems into the meta-learner (Ravi & Larochelle, 2017; Finn et al., 2017a; Husken & Goerick, 2000).”
Model-Based Reinforcement Learning via Meta-Policy Optimization (2018, background): “The last category embeds the structure of optimization problems into the meta-learning algorithm [11, 39, 40].”
Meta-learning by the Baldwin effect (2018, methodology): “ave been applied to few-shot image recognition [22] and reinforcement learning [8, 31]. More recent approaches propose to include the inductive bias of optimization-based learning into a meta-learner [13, 21, 9]. Particularly related to this work is model-agnostic meta-learning (MAML) approach [9], ”