通过吸引子动力学实现离散、组合和符号表示
Discrete, compositional, and symbolic representations through attractor dynamics
AI总结：
针对符号与次符号过程集成依赖人为假设的问题，提出一种结合吸引子动力学与符号表示的神经随机动力系统模型，通过无监督学习将连续空间划分为离散符号序列，实现了反映输入与编码互信息的统一认知建模框架。
摘要：
符号系统是建模认知过程的强大框架，因为它们封装了作为人类推理和行为许多方面基础的规则和关系。这些模型的核心在于系统性、组合性和生产性，使其在认知科学和人工智能中具有不可估量的价值。然而，某些局限性依然存在。例如，结构化符号过程与潜在次符号过程的集成已在计算层面通过量化或softmax采样等人为方法实现，这些方法假设而非推导了支撑离散化和符号化的操作。在这项工作中，我们引入了一种新颖的神经随机动力系统模型，该模型将吸引子动力学与符号表示相结合，以对类似于概率思维语言（PLoT）的认知过程进行建模。我们的模型将连续表示空间划分为离散的吸引域，其吸引子状态对应于符号序列，通过无监督学习反映了符号系统特有的语义性和组合性，而不是依赖预定义的原语。此外，与PLoT一样，我们的模型学习采样多样化的吸引子状态分布，这些状态反映了输入数据与符号编码之间的互信息。该方法建立了一个统一的框架，通过神经动力学整合了符号和次符号处理，这是一种在AI中被证明具有表达力的神经合理基底，提供了一个更全面反映认知操作复杂二重性的模型。
英文摘要：
Symbolic systems are powerful frameworks for modeling cognitive processes as they encapsulate the rules and relationships fundamental to many aspects of human reasoning and behavior. Central to these models are systematicity, compositionality, and productivity, making them invaluable in both cognitive science and artificial intelligence. However, certain limitations remain. For instance, the integration of structured symbolic processes and latent sub-symbolic processes has been implemented at the computational level through fiat methods such as quantization or softmax sampling, which assume, rather than derive, the operations underpinning discretization and symbolicization. In this work, we introduce a novel neural stochastic dynamical systems model that integrates attractor dynamics with symbolic representations to model cognitive processes akin to the probabilistic language of thought (PLoT). Our model segments the continuous representational space into discrete basins, with attractor states corresponding to symbolic sequences, that reflect the semanticity and compositionality characteristic of symbolic systems through unsupervised learning, rather than relying on pre-defined primitives. Moreover, like PLoT, our model learns to sample a diverse distribution of attractor states that reflect the mutual information between the input data and the symbolic encodings. This approach establishes a unified framework that integrates both symbolic and sub-symbolic processing through neural dynamics, a neuro-plausible substrate with proven expressivity in AI, offering a more comprehensive model that mirrors the complex duality of cognitive operations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
