Meta-learning over neural topology optimization learns initial designs that speed up convergence, yet a simpler strain-energy pretraining baseline outperforms it.
A Survey of Deep Meta-Learning
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Deep neural networks can achieve great successes when presented with large data sets and sufficient computational resources. However, their ability to learn new concepts quickly is limited. Meta-learning is one approach to address this issue, by enabling the network to learn how to learn. The field of Deep Meta-Learning advances at great speed, but lacks a unified, in-depth overview of current techniques. With this work, we aim to bridge this gap. After providing the reader with a theoretical foundation, we investigate and summarize key methods, which are categorized into i)~metric-, ii)~model-, and iii)~optimization-based techniques. In addition, we identify the main open challenges, such as performance evaluations on heterogeneous benchmarks, and reduction of the computational costs of meta-learning.
citation-role summary
citation-polarity summary
fields
cs.CE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Meta-neural Topology Optimization: Knowledge Infusion with Meta-learning
Meta-learning over neural topology optimization learns initial designs that speed up convergence, yet a simpler strain-energy pretraining baseline outperforms it.