发帖
雷达卡
摘要翻译：
有大量的现有技术研究心理过程的模型。心理学和哲学的一些研究从经验和知觉的内在角度来探讨它。其他的，如神经生物学或连接论机器，通过将大脑视为神经元的复杂回路，在那里每个神经元都是一个原始的二元回路，从外部来处理它。在这篇论文中，我们还将大脑建模为一个电路生长的地方，从出生时的原始组件集合开始，然后以自下而上的方式逐渐建立起来。当我们经历了一个可以用这种组合来描述的重复经验时，一个新的节点是由先前节点的简单组合而成的。然而，与神经网络不同的是，这些电路以“概念”或“感知”作为输入和输出。因此，增长的电路可以比作一个不断增长的λ表达式集合，这些表达式建立在另一个表达式的顶部，试图压缩感官输入，作为一种启发式，以限制其柯尔莫戈洛夫复杂性。
---
英文标题：
《The Mind Grows Circuits》
---
作者：
Rina Panigrahy, Li Zhang
---
最新提交年份：
2012
---
分类信息：
一级分类：Computer Science 计算机科学
二级分类：Artificial Intelligence 人工智能
分类描述：Covers all areas of AI except Vision, Robotics, Machine Learning, Multiagent Systems, and Computation and Language (Natural Language Processing), which have separate subject areas. In particular, includes Expert Systems, Theorem Proving (although this may overlap with Logic in Computer Science), Knowledge Representation, Planning, and Uncertainty in AI. Roughly includes material in ACM Subject Classes I.2.0, I.2.1, I.2.3, I.2.4, I.2.8, and I.2.11.
涵盖了人工智能的所有领域，除了视觉、机器人、机器学习、多智能体系统以及计算和语言（自然语言处理），这些领域有独立的学科领域。特别地，包括专家系统，定理证明（尽管这可能与计算机科学中的逻辑重叠），知识表示，规划，和人工智能中的不确定性。大致包括ACM学科类I.2.0、I.2.1、I.2.3、I.2.4、I.2.8和I.2.11中的材料。
--
一级分类：Computer Science 计算机科学
二级分类：Formal Languages and Automata Theory 形式语言与自动机理论
分类描述：Covers automata theory, formal language theory, grammars, and combinatorics on words. This roughly corresponds to ACM Subject Classes F.1.1, and F.4.3. Papers dealing with computational complexity should go to cs.CC; papers dealing with logic should go to cs.LO.
涵盖自动机理论，形式语言理论，文法，和词的组合学。这大致相当于ACM主题类F.1.1和F.4.3。处理计算复杂性的论文应该上CS.CC；处理逻辑的论文应该去CS.LO。
--
---
英文摘要：
There is a vast supply of prior art that study models for mental processes. Some studies in psychology and philosophy approach it from an inner perspective in terms of experiences and percepts. Others such as neurobiology or connectionist-machines approach it externally by viewing the mind as complex circuit of neurons where each neuron is a primitive binary circuit. In this paper, we also model the mind as a place where a circuit grows, starting as a collection of primitive components at birth and then builds up incrementally in a bottom up fashion. A new node is formed by a simple composition of prior nodes when we undergo a repeated experience that can be described by that composition. Unlike neural networks, however, these circuits take "concepts" or "percepts" as inputs and outputs. Thus the growing circuits can be likened to a growing collection of lambda expressions that are built on top of one another in an attempt to compress the sensory input as a heuristic to bound its Kolmogorov Complexity.
---
PDF链接：
https://arxiv.org/pdf/1203.0088
京公网安备 11010802022788号
