Auto-Meta: Automated Gradient Based Meta Learner Search
Explore this paper's citation graph
Summary
This work verifies that automated architecture search synergizes with the effect of gradient-based meta learning, and adopts the progressive neural architecture search to find optimal architectures for meta-learners.
- Type
- preprint
- Published
- 2018-06-11
- Cited by
- 44
- References
- 34
- Access
- Open access
- OpenAlex
- https://openalex.org/W2809234895
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:49308946
Keywords
Computer science, Meta learning (computer science), Artificial intelligence, Machine learning, Hyperparameter
References
- Human-level concept learning through probabilistic program induction
- Borg, Omega, and Kubernetes
- Designing Neural Network Architectures using Reinforcement Learning
- RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning
- Meta-Learning with Memory-Augmented Neural Networks
- Large-Scale Evolution of Image Classifiers
- Prototypical Networks for Few-shot Learning
- DeepArchitect: Automatically Designing and Training Deep Architectures
- A Simple Neural Attentive Meta-Learner
- Learning Transferable Architectures for Scalable Image Recognition
- Practical Network Blocks Design with Q-Learning
- Optimization as a Model for Few-Shot Learning
- Hierarchical Representations for Efficient Architecture Search
- Progressive Neural Architecture Search
- Regularized Evolution for Image Classifier Architecture Search
- On First-Order Meta-Learning Algorithms
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- SMASH: One-Shot Model Architecture Search through HyperNetworks
- Neural Architecture Search with Reinforcement Learning
- Genetic CNN
Cited by
- Unsupervised Learning via Meta-Learning
- Provable Guarantees for Gradient-Based Meta-Learning
- An Extensive Checklist for Building AutoML Systems
- Adaptive Gradient-Based Meta-Learning Methods
- AutoML: A Survey of the State-of-the-Art
- Meta-Learning with Implicit Gradients
- MetAdapt: Meta-Learned Task-Adaptive Architecture for Few-Shot Classification
- Meta-Learning of Neural Architectures for Few-Shot Learning
- Towards Fast Adaptation of Neural Architectures with Meta Learning
- M-NAS: Meta Neural Architecture Search
- Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?
- Meta-Learning in Neural Networks: A Survey
- A Comprehensive Overview and Survey of Recent Advances in Meta-Learning
- Gradient-EM Bayesian Meta-learning
- Functional Gradient Boosting for Learning Residual-like Networks with Statistical Guarantees
- NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing
- Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
- A survey on data‐efficient algorithms in big data era
- Across-task neural architecture search via meta learning
- Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning