Search papers, labs, and topics across Lattice.
This paper introduces Augmented Instance-Based Learning (AIBL), a novel instance-learning model that extends traditional Instance-Based Learning Theory (IBLT) to high-dimensional sequential data by leveraging neural embeddings for situation matching and incorporating structured memory stores (active, forgotten, surprise). AIBL addresses the limitations of symbolic matching in IBLT by enabling learned similarity retrieval and improves performance by dynamically managing memory through an observation-driven graduation algorithm that adapts to concept drift and handles novelty. Evaluations across five machine learning and three simulation tasks demonstrate AIBL's superior accuracy, achieving 6-17 percentage point improvements over baselines by effectively managing novelty detection, cold-start scenarios, and reward learning.
Novel memory architecture and neural embedding similarity in instance-based learning unlock significant accuracy gains and robust adaptation to concept drift.
Sequential learning systems often make decisions from accumulated experience while receiving high-dimensional inputs whose distribution may change over time. Instance-Based Learning Theory (IBLT) provides a principled case-based framework for such settings through stored situation-decision-utility instances, partial matching, activation, and blending. IBLT relies on symbolic knowledge representation in dictionary-like formats, but text, images, transaction vectors, and user-item histories often require learned similarity rather than hand-specified matching rules. In this paper, we introduce AIBL (Augmented Instance-Based Learning), an instance-learning model formulated in a learned vector space for high- dimensional sequential data. AIBL generalizes symbolic situation matching to neural embedding similarity while retaining instance storage, activation- weighted retrieval, and utility blending. The AIBL model organizes memory into active, forgotten, and surprise stores. Surprise memory separates weakly matched, possible out-of-distribution, or corner-case observations from active memory, reducing forced fitting to the nearest available cases. An observation-driven graduation algorithm promotes recurring surprise instances to active memory, allowing the memory to incorporate repeated novel patterns that may arise under concept drift. We evaluate the same implementation on five machine learning tasks and three controlled simulation tasks, comparing AIBL with classical IBLT variants and task-specific baselines where appropriate. AIBL improves accuracy by 6 to 17 percentage points. The results show where vector-space retrieval improves over symbolic matching and how the added memory mechanisms govern novelty detection, cold-start handling, drift adaptation, and reward learning under the tested protocols.
