Corpus ID: 59608630

Adaptive Posterior Learning: few-shot learning with a surprise-based memory module

@article{Ramalho2019AdaptivePL,
  title={Adaptive Posterior Learning: few-shot learning with a surprise-based memory module},
  author={Tiago Ramalho and M. Garnelo},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.02527}
}
The ability to generalize quickly from few observations is crucial for intelligent systems. [...] Key Method We show this algorithm can perform as well as state of the art baselines on few-shot classification benchmarks with a smaller memory footprint. In addition, its memory compression allows it to scale to thousands of unknown labels. Finally, we introduce a meta-learning reasoning task which is more challenging than direct classification. In this setting, APL is able to generalize with fewer than one…Expand
Generalizing from a Few Examples: A Survey on Few-Shot Learning
Episodic Memory in Lifelong Language Learning
Efficient Meta Lifelong-Learning with Limited Memory
Generalizing from a Few Examples
Learning from Very Few Samples: A Survey
Few-Shot Learning With Global Class Representations
Few-shot Continual Learning: a Brain-inspired Approach
Few Shot Learning With No Labels
Learning to Compare Relation: Semantic Alignment for Few-Shot Learning
...
1
2
...

References

SHOWING 1-10 OF 32 REFERENCES
Meta-Learning with Memory-Augmented Neural Networks
Learning to Remember Rare Events
Prototypical Networks for Few-shot Learning
Matching Networks for One Shot Learning
A Simple Neural Attentive Meta-Learner
Siamese Neural Networks for One-Shot Image Recognition
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
Relational recurrent neural networks
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Scaling learning algorithms towards AI
...
1
2
3
4
...