2019/02/07 by Tiago Ramalho, Marta Garnelo, Ramalho, Tiago +1 · 10 citations
Computer Science · Mathematics · #Algorithm #Artificial intelligence #Auxiliary memory #Bayesian Modeling and Causal Inference #Class (philosophy) #Computer science #Domain Adaptation and Few-Shot Learning #Encoding (memory) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Machine learning #Memory footprint #One shot #Programming language #Recall #Shot (pellet) #State (computer science) #Surprise #Task (project management) #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1902.02527
published in arXiv (Cornell University) (Cornell University) · ICLR 2019
arxiv created 2019/02/07 · openalex publication_date 2019/02/07 · arxiv updated 2019/02/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
The ability to generalize quickly from few observations is crucial for intelligent systems. In this paper we introduce APL, an algorithm that approximates probability distributions by remembering the most surprising observations it has encountered. These past observations are recalled from an external memory module and processed by a decoder network that can combine information from different memory slots to generalize beyond direct recall. 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 example per class via deductive reasoning.