arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.11665cs.NEcs.AI
收藏

超越LLM、稀疏分布式记忆和神经形态计算:一种用于超高速、超低功耗和低成本的超维SRAM-CAM“VaCoAl”

Beyond LLMs, Sparse Distributed Memory, and Neuromorphics <A Hyper-Dimensional SRAM-CAM "VaCoAl" for Ultra-High Speed, Ultra-Low Power, and Low Cost>

Hitotsubashi University(立命馆大学);Meisei University(立命馆大学);Shuhari System(Shuhari系统)

Hiroyuki Chuma, Kanji Otsuka, Yoichi Sato

AI总结:

本文提出VaCoAl算法,通过超维计算和伽罗瓦域扩散,在SRAM/DRAM-CAM上实现可逆、可审计的多跳推理,解决灾难性遗忘和绑定问题,并在维基数据上验证了其路径依赖的STDP式选择机制。

摘要:

本文报告了一个意外发现:在一个确定性超维计算(HDC)架构中,该架构反转了伽罗瓦域代数的传统角色——不是将其用于纠错以获得唯一答案,而是作为相对相似性和路径质量排序的引擎——出现了一种路径依赖的语义选择机制,等效于尖峰时序依赖可塑性(STDP),其幅度可通过封闭形式表达式先验预测,并与测量值匹配。为了解决灾难性遗忘、学习停滞和绑定问题,我们在代数层面提出了VaCoAl(模糊巧合算法)及其Python实现PyVaCoAl,运行于超高维SRAM/DRAM-CAM上。该算法根植于稀疏分布式记忆,通过伽罗瓦域扩散解决高维二进制空间中的正交化和检索问题,实现低负载部署。关键的是,VaCoAl将认知边界——前沿大小——嵌入其架构中,通过路径积分置信度(CR2)对候选进行排序,以实现组合泛化;这种有限理性设计产生了STDP式的选择,而纠错范式在结构上无法实现。我们评估了来自Wikidata的约47万条导师-学生关系上的多跳推理,追踪了多达57代(超过2550万条路径)。基于CR去噪的HDC捆绑和解绑操作量化了概念在DAG上的传播。结果显示了对牛顿-莱布尼茨争议的重新解释,以及从稀疏收敛到后莱布尼茨“超级高速公路”的相变,结构指标支持库恩范式转变。VaCoAl因此定义了第三范式——HDC-AI,以可逆、可审计的多跳推理补充LLM。

英文摘要:

VaCoAl (Python: PyVaCoAl) attacks the Binding Problem algebraically rather than statistically: an SRAM/DRAM-CAM organised end-to-end around one primitive, XOR-and-shift over GF(2) via primitive-polynomial LFSRs. Rooted in Kanerva's Sparse Distributed Memory, it retrieves in a million-dimensional binary space by Galois-field diffusion; Binding and Unbinding are exactly reversible at O(L), giving compositional generalisation with post-hoc auditability. Unexpectedly, a path-dependent semantic selection mechanism emerges undesigned, functionally equivalent to Spike-Timing-Dependent Plasticity (STDP) and predictable a priori from a closed form matching measurement on tens of millions of records. It is the Don't Care (collision-tolerance) rule: not a defect to engineer away, but the source of its ability to rank paths by quality. Capability: reversible binding plus tolerated collisions yields a path-integral confidence measure (CR2) ranking candidates by accumulated reliability, absent from hash-based search. Necessity: repair the collisions fully and the ranking vanishes; a memory that never fails has no record of which paths were difficult. Position: we do not surpass large language models; the substrate is orthogonal, supplying the auditable path-ranking layer they lack. A mentor-student ontology of ~470,000 WIKIDATA scholars, traversed backwards from all 64 Fields Medalists to depth 57 and >25.5M paths, stress-tests multi-hop reasoning over a large DAG. Ablation shows Don't Care imposing a depth-dependent exponential penalty that prunes circuitous routes and preserves direct ones: an Occam's razor. Per-generation CR1 stays within 0.995-0.999, yet cumulative CR2 decays monotonically to ~0.905 by generation 56, matching the closed form 0.997^56 = 0.846 within observed variation. All measurements are from PyVaCoAl, a software DRAM-CAM; speed and power figures are projections.

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。

↑