用模块化神经网络实现可解释的确定性算法计算
Modular Neural Computer
- 通过固定结构的模块与外部记忆实现算法编译
- 在数组最小值、排序和A*搜索中保持精确行为
- 适合需要可解释性与确定性的算法学习场景
本文提出模块化神经计算机（MNC），一种用于变量长度输入的精确算法计算的记忆增强神经架构。该模型结合外部标量记忆单元、显式读写头、控制器多层感知机（MLP）以及一组同质的功能性MLP模块。不同于从数据端到端学习算法，MNC通过解析指定的神经组件实现给定算法，各组件具有固定接口和精确行为。控制流通过独热模块门在神经计算中表示，未激活模块被抑制。计算过程表现为由固定图生成的一系列记忆变换。通过三个案例研究展示：求数组最小值、原地排序数组、在固定问题实例上执行A*搜索。这些示例表明，算法过程可编译为带外部记忆的模块化神经组件，同时保持确定性行为和明确的中间状态。
原文摘要 · Abstract (English)
This paper introduces the Modular Neural Computer (MNC), a memory-augmented neural architecture for exact algorithmic computation on variable-length inputs. The model combines an external associative memory of scalar cells, explicit read and write heads, a controller multi-layer perceptron (MLP), and a homogeneous set of functional MLP modules. Rather than learning an algorithm end to end from data, it realizes a given algorithm through analytically specified neural components with fixed interfaces and exact behavior. The control flow is represented inside the neural computation through one-hot module gates, where inactive modules are inhibited. Computation unfolds as a sequence of memory transformations generated by a fixed graph. The architecture is illustrated through three case studies: computing the minimum of an array, sorting an array in place, and executing A* search on a fixed problem instance. These examples show that algorithmic procedures can be compiled into modular neural components with external memory while preserving deterministic behavior and explicit intermediate state.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。