Skip to main content
QUICK REVIEW

[论文解读] The whole brain architecture approach: Accelerating the development of artificial general intelligence by referring to the brain

Hiroshi Yamakawa|arXiv (Cornell University)|Mar 6, 2021
EEG and Brain-Computer Interfaces参考文献 66被引用 24
一句话总结

本文提出整体大脑架构(WBA)方法,通过使用大脑参考架构(BRA)来约束和指导软件设计,以加速通用人工智能(AGI)的发展。基于BRA的开发框架将脑启发式AGI设计分解为BRA创建——采用结构约束接口分解(SCID)方法构建生物上合理的组件图——使具备有限神经科学专业知识的开发者也能实现类脑认知系统。

ABSTRACT

The vastness of the design space created by the combination of a large number of computational mechanisms, including machine learning, is an obstacle to creating an artificial general intelligence (AGI). Brain-inspired AGI development, in other words, cutting down the design space to look more like a biological brain, which is an existing model of a general intelligence, is a promising plan for solving this problem. However, it is difficult for an individual to design a software program that corresponds to the entire brain because the neuroscientific data required to understand the architecture of the brain are extensive and complicated. The whole-brain architecture approach divides the brain-inspired AGI development process into the task of designing the brain reference architecture (BRA) -- the flow of information and the diagram of corresponding components -- and the task of developing each component using the BRA. This is called BRA-driven development. Another difficulty lies in the extraction of the operating principles necessary for reproducing the cognitive-behavioral function of the brain from neuroscience data. Therefore, this study proposes the Structure-constrained Interface Decomposition (SCID) method, which is a hypothesis-building method for creating a hypothetical component diagram consistent with neuroscientific findings. The application of this approach has begun for building various regions of the brain. Moving forward, we will examine methods of evaluating the biological plausibility of brain-inspired software. This evaluation will also be used to prioritize different computational mechanisms, which should be merged, associated with the same regions of the brain.

研究动机与目标

  • 通过参考大脑架构来解决AGI开发中庞大而难以处理的设计空间问题。
  • 通过将大脑架构标准化为可重用的大脑参考架构(BRA),使非专家开发者能够构建脑启发式AGI。
  • 通过开发SCID方法来构建与大脑解剖结构一致的假设性组件图,以克服神经科学知识的不完整性。
  • 建立一个可扩展、模块化的框架,用于将计算机制整合到整体大脑软件系统中。
  • 评估脑启发式软件的生物合理性,以指导其向人类水平AGI收敛。

提出的方法

  • BRA驱动开发:将BRA设计与实现解耦,支持跨项目复用。
  • 大脑参考架构(BRA)由两个核心组件构成:大脑信息流(BIF),即神经回路的有向图;以及假设性组件图(HCD),即功能依赖关系图。
  • 结构约束接口分解(SCID)方法通过从解剖约束中推断组件接口,生成HCD,即使在神经科学数据不完整的情况下也能实现。
  • SCID利用结构约束(如连接模式)指导组件分解,同时保持功能一致性。
  • BRA在中观尺度上设计,以平衡细节与抽象性,避免低层次神经生理噪声的干扰。
  • 该框架支持合并式开发,以整合多样化的计算机制,并减少设计空间的分歧。

实验结果

研究问题

  • RQ1如何有效约束人工通用智能的设计空间,以加速其开发?
  • RQ2在神经科学知识不完整的情况下,何种方法能够实现生物上合理的组件图构建?
  • RQ3非专业人员如何在缺乏神经科学专业知识的情况下开发脑启发式AGI软件?
  • RQ4何种评估标准可确保脑启发式AI系统的生物合理性?
  • RQ5如何将多样化的计算机制整合到统一的整体大脑架构中?

主要发现

  • BRA驱动开发框架通过提供标准化、可重用的架构约束,使非专家能够实现脑启发式AGI。
  • SCID方法成功生成了与已知大脑解剖结构一致的假设性组件图(HCD),即使功能数据有限。
  • BRA通过以标准、环境无关的格式描述大脑架构,支持模块化与可重用性。
  • 该框架可容忍多种可能冲突的HCD,只要其满足最低有效性标准,即可保留设计空间的多样性。
  • 提出将生物合理性评估作为关键机制,以指导整合并推动向人类水平AGI的收敛。
  • 该方法为大规模整体大脑软件开发建立了可扩展的框架,具有统一当前分散的AGI研究努力的潜力。

更好的研究,从现在开始

从论文设计到论文写作,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。