Active perception and disentangled representations allow continual, episodic zero and few-shot learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rawlinson, David, Kowadlo, Gideon
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908848397221888
author Rawlinson, David
Kowadlo, Gideon
author_facet Rawlinson, David
Kowadlo, Gideon
contents Generalization is often regarded as an essential property of machine learning systems. However, perhaps not every component of a system needs to generalize. Training models for generalization typically produces entangled representations at the boundaries of entities or classes, which can lead to destructive interference when rapid, high-magnitude updates are required for continual or few-shot learning. Techniques for fast learning with non-interfering representations exist, but they generally fail to generalize. Here, we describe a Complementary Learning System (CLS) in which the fast learner entirely foregoes generalization in exchange for continual zero-shot and few-shot learning. Unlike most CLS approaches, which use episodic memory primarily for replay and consolidation, our fast, disentangled learner operates as a parallel reasoning system. The fast learner can overcome observation variability and uncertainty by leveraging a conventional slow, statistical learner within an active perception system: A contextual bias provided by the fast learner induces the slow learner to encode novel stimuli in familiar, generalized terms, enabling zero-shot and few-shot learning. This architecture demonstrates that fast, context-driven reasoning can coexist with slow, structured generalization, providing a pathway for robust continual learning.
format Preprint
id arxiv_https___arxiv_org_abs_2602_19355
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Active perception and disentangled representations allow continual, episodic zero and few-shot learning
Rawlinson, David
Kowadlo, Gideon
Machine Learning
Artificial Intelligence
68Q05 68T05 90C40 68T30 92C20
I.2.6; I.2.4; F.1.1; I.2.8
Generalization is often regarded as an essential property of machine learning systems. However, perhaps not every component of a system needs to generalize. Training models for generalization typically produces entangled representations at the boundaries of entities or classes, which can lead to destructive interference when rapid, high-magnitude updates are required for continual or few-shot learning. Techniques for fast learning with non-interfering representations exist, but they generally fail to generalize. Here, we describe a Complementary Learning System (CLS) in which the fast learner entirely foregoes generalization in exchange for continual zero-shot and few-shot learning. Unlike most CLS approaches, which use episodic memory primarily for replay and consolidation, our fast, disentangled learner operates as a parallel reasoning system. The fast learner can overcome observation variability and uncertainty by leveraging a conventional slow, statistical learner within an active perception system: A contextual bias provided by the fast learner induces the slow learner to encode novel stimuli in familiar, generalized terms, enabling zero-shot and few-shot learning. This architecture demonstrates that fast, context-driven reasoning can coexist with slow, structured generalization, providing a pathway for robust continual learning.
title Active perception and disentangled representations allow continual, episodic zero and few-shot learning
topic Machine Learning
Artificial Intelligence
68Q05 68T05 90C40 68T30 92C20
I.2.6; I.2.4; F.1.1; I.2.8
url https://arxiv.org/abs/2602.19355