Abstract, or disentangled, representations are a promising mathematical framework for efficient and effective generalization in both biological and artificial systems. We investigate abstract representations in the context of multi-task classification over noisy evidence streams -- a canonical decision-making neuroscience paradigm. We derive theoretical bounds that guarantee the emergence of disentangled representations in the latent state of any optimal multi-task classifier, when the number of tasks exceeds the dimensionality of the state space. We experimentally confirm that RNNs trained on multi-task classification learn disentangled representations in the form of continuous attractors, leading to zero-shot out-of-distribution (OOD) generalization. We demonstrate the flexibility of the abstract RNN representations across various decision boundary geometries and in tasks requiring classification confidence estimation. Our framework suggests a general principle for the formation of cognitive maps that organize knowledge to enable flexible generalization in biological and artificial systems alike, and closely relates to representations found in humans and animals during decision-making and spatial reasoning tasks.

翻译：抽象或解耦表征是一种有前景的数学框架，可为生物与人工系统实现高效且有效的泛化能力。本研究在多任务分类背景下探究噪声证据流中的抽象表征——这是决策神经科学领域的经典范式。我们推导出理论边界，证明当任务数量超过状态空间维度时，任何最优多任务分类器的潜在状态中必然会出现解耦表征。实验证实，经过多任务分类训练的循环神经网络能够以连续吸引子的形式学习解耦表征，从而实现分布外场景下的零样本泛化。我们展示了抽象循环神经网络表征在不同决策边界几何形态中的适应性，以及在需要分类置信度估计任务中的表现。本框架揭示了认知图谱形成的一般原理：通过知识组织实现生物与人工系统的灵活泛化，该表征机制与人类和动物在决策及空间推理任务中发现的表征模式高度相关。