An integrative computational architecture for object-driven cortex.
An integrative computational architecture for object-driven cortex.
复制标题
对象驱动皮层的综合计算架构。
DOI：
10.1016/j.conb.2019.01.010
复制
发表时间：
2019
影响因子：
5.7
通讯作者：
Tenenbaum,Joshua
中科院分区：
文献类型：
--
作者：
Yildirim,Ilker;Wu,Jiajun;Kanwisher,Nancy;Tenenbaum,Joshua
HighlightsObjects in motion activate multiple cortex regions in every lobe of human brain.We outline a integrated computational architecture for this“object-driven”cortex.Architecture components derived from the recent advances in machine learning and AI.Points towards a neuroally grounded，functional account of dynamic object cognition.Computational architecture for object-driven cortex运动中的物体激活人脑每个叶中的多个皮层区域。这些区域是否代表了一个独立系统的集合，或者是否存在一个跨越所有对象驱动皮层的总体功能架构？受人工智能（AI），机器学习和认知科学的最新工作的启发，我们认为这些区域可以被理解为一个连贯的网络，实现一个综合的计算系统，统一的功能需要感知，预测，推理，并计划与物理对象的使用或制作工具的范例情况下。我们的提案借鉴了一个建模框架，该框架结合了多种人工智能方法，包括因果生成模型，混合符号连续规划算法和神经识别网络，以及以对象为中心的基于物理的表示。我们回顾了我们的建议的特定组件的特定区域，包括对象驱动的皮层相关的证据，并制定了未来的研究方向，目标是建立一个完整的功能和机制，这个系统的帐户。
HighlightsObjects in motion activate multiple cortical regions in every lobe of the human brain.We outline an integrative computational architecture for this ‘object-driven’cortex.Architecture components derive from recent advances in machine learning and AI.Points toward a neurally grounded, functional account of dynamic object cognition.Computational architecture for object-driven cortexObjects in motion activate multiple cortical regions in every lobe of the human brain. Do these regions represent a collection of independent systems, or is there an overarching functional architecture spanning all of object-driven cortex? Inspired by recent work in artificial intelligence (AI), machine learning, and cognitive science, we consider the hypothesis that these regions can be understood as a coherent network implementing an integrative computational system that unifies the functions needed to perceive, predict, reason about, and plan with physical objects—as in the paradigmatic case of using or making tools. Our proposal draws on a modeling framework that combines multiple AI methods, including causal generative models, hybrid symbolic-continuous planning algorithms, and neural recognition networks, with object-centric, physics-based representations. We review evidence relating specific components of our proposal to the specific regions that comprise object-driven cortex, and lay out future research directions with the goal of building a complete functional and mechanistic account of this system.