General Neurodynamic Associative Memory Model

一般神经动力学联想记忆模型

• 批准号: RGPIN-2014-04069
• 负责人: Chartier, Sylvain
• 金额: $ 2.19万
• 依托单位: University of Ottawa
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2015
• 资助国家: 加拿大
• 起止时间: 2015-01-01 至 2016-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=587583
• 关键词: General; Neurodynamic; Associative; Memory; Model

Although it is something most of us do every day without effort, memorizing is in fact an incredibly complex task. For instance, the simple act of storing and retrieving an object is something we have not yet managed to program a machine to do with anything approaching human efficiency and robustness. My research aims to better understand how human cognitive system accomplishes the complex task of create (and enhance) representation from patterns as well as recognize, identify, categorize and classify them. In particular, this research focuses on an interesting nonlinear dynamics system perspective where time and change are the key variables. Within that perspective memory are represented as invariant states of the system. To understand how the human cognitive system works, we need to develop formal models. Nowadays, no formal models can take into account this variety of behavior without scarifying simplicity and self-consistency. In this research, we will use artificial neural networks that are parallel and where information is distributed among the units. Since the brain uses similar computing units and mechanisms for different tasks, this approach uses a general bidirectional associative memory model as building blocks for a general cognitive architecture. This research aims to take into account unsupervised, unsupervised and reinforcement learning using a unique model. The model must have the flexibility to adapt itself in regards to neuroscience and cognition constraints. It is hoped that by developing a general bidirectional associative memory we will have a better understanding on how the mind works and how this understanding can be translated into computational intelligence

虽然我们大多数人每天都在做一些不费力的事情，但记忆实际上是一项非常复杂的任务。例如，存储和检索对象的简单行为是我们还没有设法编程机器来做任何接近人类效率和鲁棒性的事情。 我的研究旨在更好地理解人类认知系统如何完成从模式中创建（和增强）表示的复杂任务，以及识别，识别，分类和分类它们。特别是，这项研究侧重于一个有趣的非线性动力学系统的角度来看，时间和变化是关键变量。在透视图中，记忆被表示为系统的不变状态。 为了理解人类认知系统是如何工作的，我们需要开发形式化的模型。如今，没有一个正式的模型能够在不牺牲简单性和自洽性的情况下考虑到这种行为的多样性。在这项研究中，我们将使用并行的人工神经网络，其中信息分布在单元之间。由于大脑使用类似的计算单元和机制来执行不同的任务，因此这种方法使用通用的双向联想记忆模型作为通用认知架构的构建块。这项研究旨在使用独特的模型考虑无监督，无监督和强化学习。该模型必须具有灵活性，以适应神经科学和认知约束。希望通过开发一个通用的双向联想记忆，我们将有一个更好的了解如何在头脑的工作，以及如何将这种理解可以转化为计算智能