Adaptive Posterior Learning: few-shot learning with a surprise-based memory module
This addresses the problem of rapid generalization from few observations for intelligent systems, with incremental improvements in memory efficiency and scalability.
The paper tackles few-shot learning by introducing APL, an algorithm that uses a surprise-based memory module to approximate probability distributions and recall past observations, achieving performance comparable to state-of-the-art baselines with a smaller memory footprint and scaling to thousands of unknown labels.
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.