用于量化模拟回写和可解释程序执行的符号神经CPU
A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Execution
浏览论文内容
中文总结 AI 辅助
研究神经网络执行器状态转换不可见问题，提出符号神经CPU架构，结合多种技术实现可解释、低精度和可控神经执行，在基准测试中表现良好，消融实验明确关键因素，扩展接口建立跟踪可验证框架。
中文摘要 AI 辅助
神经网络可学习算法输入输出映射，但信任其执行器不仅需正确结果，因其状态转换常不可见。为此引入跟踪监督符号神经CPU，这是一种分解式学习执行架构，结合循环控制、固定可微算术逻辑单元库上的显式操作路由器、目标掩码寄存器回写、完整轨迹监督和匹配定点重放。该模型展示每一步所选操作、源和目标寄存器、寄存器轨迹、内存信号和回写语义。在主要基准测试中，非量化执行器能精确重现参考执行，八位量化模拟执行器在1000条指令程序中保留符号操作路径。与匹配定点重放评估时，残余数值漂移消失。比较了多种控制器，消融实验表明操作门监督对可检查执行路径必要。还扩展了接口，这些结果建立了可解释、低精度和可控神经执行的跟踪可验证框架。
英文摘要
Neural networks can learn algorithmic input-output mappings, but trusting a learned executor requires more than a correct final answer because the state transitions that produce it are usually hidden. To make those transitions visible, we introduce a trace-supervised symbolic neural CPU, a factorized learned execution architecture that combines recurrent control, an explicit operation router over a fixed differentiable arithmetic-logic unit bank, destination-masked register writeback, complete trajectory supervision and matched fixed-point replay. The model exposes the selected operation, source and destination registers, register trajectory, memory signals and writeback semantics at every step. On the principal 16-wide benchmark, the non-quantized executor reproduces reference execution exactly, while the eight-bit quantization-simulated executor preserves the symbolic operation path through programs of 1,000 instructions. When the same execution is evaluated against a matched fixed-point replay, the residual numerical drift disappears, showing that it comes from a mismatch between continuous and low-precision reference semantics rather than from execution failure. We compare recurrent, Transformer, temporal-convolution, temporal graph-inspired and state-space controllers, and the ablations show that operation-gate supervision is necessary for an inspectable execution path. Hidden-opcode memory-pressure tasks expose the remaining limits in delayed state use and temporal binding. We also extend the interface with ValueMemory, hybrid adaptive leaky integrate-and-fire controllers, candidate-constrained symbolic control trained through behaviour cloning and actor-critic reinforcement learning, and an RV32I base-integer semantic bridge. Together, these results establish a trace-verifiable framework for interpretable, low-precision and controllable neural execution.
发表机构
- Federal University of Bahia（巴伊亚联邦大学）
机构由 AI 辅助整理，请以论文原文为准。
