Using neural networks to understand the information that guides behavior: a case study in visual navigation.
Using neural networks to understand the information that guides behavior: a case study in visual navigation.
复制标题
DOI：
10.1007/978-1-4939-2239-0_14
复制
发表时间：
2015
影响因子：
--
通讯作者：
Andrew O. Philippides;P. Graham;Bart Baddeley;P. Husbands
中科院分区：
文献类型：
--
作者：
Andrew O. Philippides;P. Graham;Bart Baddeley;P. Husbands
为了表现出健壮和适应性，动物必须有效地提取与任务相关的感官信息。了解它们如何做到这一点的一种方法是探索动物在自然行为中感知到的信息中的信息。在本章中，我们将描述如何使用人工神经网络（ANN）来探索视觉和记忆的效率，这可能是复杂世界中视觉引导路线导航的基础。具体来说，我们使用三种类型的神经网络来学习在单个路线遍历（训练路线）期间遇到的一系列视图中的知识，以这种方式，网络输出呈现给它们的新视图的熟悉度。导航的问题，然后在搜索熟悉的意见，即类似的意见与路线。这种方法有两个主要好处。首先，人工神经网络提供了一个紧凑的整体表示的数据，因此是一个有效的方式来编码一个大的视图集。其次，由于我们不存储训练视图，因此我们使用的训练视图的数量不受限制，并且代理不需要决定要学习哪些视图。
To behave in a robust and adaptive way, animals must extract task-relevant sensory information efficiently. One way to understand how they achieve this is to explore regularities within the information animals perceive during natural behavior. In this chapter, we describe how we have used artificial neural networks (ANNs) to explore efficiencies in vision and memory that might underpin visually guided route navigation in complex worlds. Specifically, we use three types of neural network to learn the regularities within a series of views encountered during a single route traversal (the training route), in such a way that the networks output the familiarity of novel views presented to them. The problem of navigation is then reframed in terms of a search for familiar views, that is, views similar to those associated with the route. This approach has two major benefits. First, the ANN provides a compact holistic representation of the data and is thus an efficient way to encode a large set of views. Second, as we do not store the training views, we are not limited in the number of training views we use and the agent does not need to decide which views to learn.