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

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

7 Feb 2019ICLR 2019 5arXiv:1902.02527archive 2025-07-28

Tiago Ramalho, Marta Garnelo

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

cogentlabs/apl officialmentioned in paperpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderFew-Shot LearningGeneral ClassificationMeta-Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification OMNIGLOT - 1-Shot, 1000 way APL Accuracy 68.9 #1 of 1 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way APL Accuracy 97.2% #8 of 20 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 423 way APL Accuracy 73.5 #1 of 1 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 5-way APL Accuracy 97.9 #16 of 17 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 1000 way APL Accuracy 78.9 #1 of 1 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 20-way APL Accuracy 97.6% #17 of 19 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 423 way APL Accuracy 88 #1 of 1 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 5-way APL Accuracy 99.9 #3 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections