# Unsupervised Progressive Learning and the STAM Architecture

Source: [Unsupervised Progressive Learning and the STAM Architecture](<https://www.sota2.com/research/paper/68fa5f121e209131ce9e74b7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T19:07:52.793Z

Authors: James Smith, Cameron Taylor, Seth Baer, Constantine Dovrolis

Published: 2019-04-03T14:25:08.000Z

## Abstract

We first pose the Unsupervised Progressive Learning (UPL) problem: an online representation learning problem in which the learner observes a non-stationary and unlabeled data stream, learning a growing number of features that persist over time even though the data is not stored or replayed. To solve the UPL problem we propose the Self-Taught Associative Memory (STAM) architecture. Layered hierarchies of STAM modules learn based on a combination of online clustering, novelty detection, forgetting outliers, and storing only prototypical features rather than specific examples. We evaluate STAM representations using clustering and classification tasks. While there are no existing learning scenarios that are directly comparable to UPL, we compare the STAM architecture with two recent continual learning models, Memory Aware Synapses (MAS) and Gradient Episodic Memories (GEM), after adapting them in the UPL setting.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Unsupervised Continual Clustering on CIFAR-100](<https://www.sota2.com/research/sota/unsupervised-continual-clustering-on-cifar-100.md>): Unsupervised Continual Clustering; CIFAR-100; Accuracy: 25.34.

- [Unsupervised Continual Clustering on Tiny-ImageNet](<https://www.sota2.com/research/sota/unsupervised-continual-clustering-on-tiny-imagenet.md>): Unsupervised Continual Clustering; Tiny-ImageNet; Clustering Accuracy (ACC): 9.21.

- [Unsupervised Continual Clustering on ImageNet 100](<https://www.sota2.com/research/sota/unsupervised-continual-clustering-on-imagenet-100.md>): Unsupervised Continual Clustering; ImageNet-100; Accuracy (ACC): 28.76.

- [Unsupervised Continual Clustering on CIFAR-10](<https://www.sota2.com/research/sota/unsupervised-continual-clustering-on-cifar-10.md>): Unsupervised Continual Clustering; CIFAR-10; Accuracy (ACC): 39.61.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1904.02021>)

[PDF](<https://arxiv.org/pdf/1904.02021.pdf>)