元学习驱动神经网络：深度学习挑战与应用综述

需积分: 1 79 浏览量更新于2024-06-16 收藏 830KB PDF 举报

元学习在神经网络领域的应用已经成为近年来人工智能研究中的一个热点话题。元学习，也被称为学习到学习，与传统的机器学习方法不同，它并非单纯地为每个任务设计独立的学习算法，而是寻求一种能够从多个学习经验中自我改进的通用学习策略。这种框架旨在解决深度学习中常见的问题，如数据稀缺、计算资源限制以及模型泛化能力的提升。本文首先定义了元学习的概念，并将其与相关领域进行了对比，如迁移学习和超参数优化。迁移学习侧重于在一个任务中学到的知识如何转移到其他任务上，而元学习则更进一步，是通过学习如何学习来增强跨任务的适应性。超参数优化则是调整模型参数以最大化性能，而元学习关注的是学习过程本身。接着，作者提出了一种新的元学习分类体系，该体系更为全面地剖析了当前元学习方法的多样性，包括基于模型的方法（如神经网络架构搜索）、基于优化的方法（如梯度元学习）和基于记忆的方法（如记忆增强的元学习）。这些方法各有特色，如基于模型的方法试图通过搜索生成有效的模型结构，基于优化的方法则聚焦于改进学习算法的参数更新策略，而基于记忆的方法则强调利用历史经验加速学习过程。在实际应用方面，元学习展示了强大的潜力，尤其是在小样本学习和强化学习领域。例如，通过元学习，模型能够在处理少量标记数据的情况下达到良好的性能，这在许多现实场景中具有显著优势。在强化学习中，元学习允许智能体快速适应新环境，提高了学习效率和效果。然而，尽管取得了显著进展，元学习仍面临诸多挑战，如学习效率低下、对任务分布的假设过于理想化、以及如何处理非静态的环境等。未来的研究方向可能集中在更高效的元学习算法设计、更加灵活的适应性模型、以及在更多实际场景中的部署验证上。总结来说，元学习在神经网络领域的应用是一门交叉学科，它不仅推动了深度学习的理论边界，还在实际问题解决中展现出了强大的实用价值。随着技术的发展，我们期待看到更多的创新和突破，以克服当前的局限并进一步提升人工智能的整体能力。

a source model to be robust to such domain-shift without

further adaptation. Many knowledge transfer methods have

been studied [34], [58] to boost target domain performance.

However, as for TL, vanilla DA and DG don’t use a meta-

objective to optimize ‘how to learn’ across domains. Mean-

while, meta-learning methods can be used to perform both

DA [59] and DG [42] (see Sec. 5.8).

Continual learning (CL) Continual or lifelong learning

[60]–[62] refers to the ability to learn on a sequence of tasks

drawn from a potentially non-stationary distribution, and

in particular seek to do so while accelerating learning new

tasks and without forgetting old tasks. Similarly to meta-

learning, a task distribution is considered, and the goal is

partly to accelerate learning of a target task. However most

continual learning methodologies are not meta-learning

methodologies since this meta objective is not solved for

explicitly. Nevertheless, meta-learning provides a potential

framework to advance continual learning, and a few recent

studies have begun to do so by developing meta-objectives

that encode continual learning performance [63]–[65].

Multi-Task Learning (MTL) aims to jointly learn sev-

eral related tasks, to beneﬁt from regularization due to

parameter sharing and the diversity of the resulting shared

representation [66]–[68], as well as compute/memory sav-

ings. Like TL, DA, and CL, conventional MTL is a single-

level optimization without a meta-objective. Furthermore,

the goal of MTL is to solve a ﬁxed number of known tasks,

whereas the point of meta-learning is often to solve unseen

future tasks. Nonetheless, meta-learning can be brought in

to beneﬁt MTL, e.g. by learning the relatedness between

tasks [69], or how to prioritise among multiple tasks [70].

Hyperparameter Optimization (HO) is within the remit

of meta-learning, in that hyperparameters like learning rate

or regularization strength describe ‘how to learn’. Here we

include HO tasks that deﬁne a meta objective that is trained

end-to-end with neural networks, such as gradient-based

hyperparameter learning [69], [71] and neural architecture

search [18]. But we exclude other approaches like random

search [72] and Bayesian Hyperparameter Optimization

[73], which are rarely considered to be meta-learning.

Hierarchical Bayesian Models (HBM) involve Bayesian

learning of parameters θ under a prior p(θ|ω). The prior

is written as a conditional density on some other variable

ω which has its own prior p(ω). Hierarchical Bayesian

models feature strongly as models for grouped data D =

|i = 1, 2, . . . , M}, where each group i has its own

. The full model is

i=1

p(D

|θ

)p(θ

|ω)

p(ω). The lev-

els of hierarchy can be increased further; in particular ω

can itself be parameterized, and hence p(ω) can be learnt.

Learning is usually full-pipeline, but using some form of

Bayesian marginalisation to compute the posterior over

ω: P (ω|D) ∼ p(ω)

i=1

dθ

p(D

|θ

)p(θ

|ω). The ease of

doing the marginalisation depends on the model: in some

(e.g. Latent Dirichlet Allocation [74]) the marginalisation is

exact due to the choice of conjugate exponential models,

in others (see e.g. [75]), a stochastic variational approach is

used to calculate an approximate posterior, from which a

lower bound to the marginal likelihood is computed.

Bayesian hierarchical models provide a valuable view-

point for meta-learning, by providing a modeling rather

than an algorithmic framework for understanding the meta-

learning process. In practice, prior work in HBMs has typi-

cally focused on learning simple tractable models θ while

most meta-learning work considers complex inner-loop

learning processes, involving many iterations. Nonetheless,

some meta-learning methods like MAML [16] can be under-

stood through the lens of HBMs [76].

AutoML: AutoML [31]–[33] is a rather broad umbrella

for approaches aiming to automate parts of the machine

learning process that are typically manual, such as data

preparation, algorithm selection, hyper-parameter tuning,

and architecture search. AutoML often makes use of numer-

ous heuristics outside the scope of meta-learning as deﬁned

here, and focuses on tasks such as data cleaning that are

less central to meta-learning. However, AutoML sometimes

makes use of end-to-end optimization of a meta-objective,

so meta-learning can be seen as a specialization of AutoML.

3 TAXONOMY

3.1 Previous Taxonomies

Previous [77], [78] categorizations of meta-learning meth-

ods have tended to produce a three-way taxonomy across

optimization-based methods, model-based (or black box)

methods, and metric-based (or non-parametric) methods.

Optimization Optimization-based methods include those

where the inner-level task (Eq. 6) is literally solved as

an optimization problem, and focuses on extracting meta-

knowledge ω required to improve optimization perfor-

mance. A famous example is MAML [16], which aims to

learn the initialization ω = θ

, such that a small number

of inner steps produces a classiﬁer that performs well on

validation data. This is also performed by gradient descent,

differentiating through the updates of the base model. More

elaborate alternatives also learn step sizes [79], [80] or

train recurrent networks to predict steps from gradients

[19], [39], [81]. Meta-optimization by gradient over long

inner optimizations leads to several compute and memory

challenges which are discussed in Section 6. A uniﬁed view

of gradient-based meta learning expressing many existing

methods as special cases of a generalized inner loop meta-

learning framework has been proposed [82].

Black Box / Model-based In model-based (or black-box)

methods the inner learning step (Eq. 6, Eq. 4) is wrapped up

in the feed-forward pass of a single model, as illustrated

in Eq. 7. The model embeds the current dataset D into

activation state, with predictions for test data being made

based on this state. Typical architectures include recurrent

networks [39], [51], convolutional networks [38] or hyper-

networks [83], [84] that embed training instances and labels

of a given task to deﬁne a predictor for test samples. In this

case all the inner-level learning is contained in the activation

states of the model and is entirely feed-forward. Outer-

level learning is performed with ω containing the CNN,

RNN or hypernetwork parameters. The outer and inner-

level optimizations are tightly coupled as ω and D directly

specify θ. Memory-augmented neural networks [85] use an

explicit storage buffer and can be seen as a model-based

剩余19页未读，继续阅读

稽函数

粉丝: 8
资源: 33

元学习驱动神经网络：深度学习挑战与应用综述

神经网络学习的应用

神经网络中的元学习综述

忆阻器在人工神经网络方面的研究应用.pdf

BP神经网络在管网漏失方面的应用.pdf

卷积神经网络在入侵检测方面的应用.pdf

尖峰神经网络深度学习研究及其应用

深度学习与卷积神经网络在AI中的应用

深度学习中的神经网络原理与应用

深度学习与卷积神经网络在脑映射中的应用

深度学习与卷积神经网络在股票预测中的应用

最新资源