论文标题
用于评估监督学习网络中神经输入表示形式的指标
A Metric for Evaluating Neural Input Representation in Supervised Learning Networks
论文作者
论文摘要
长期以来，监督的学习一直归因于大脑内的几个前馈神经回路，注意小脑颗粒层。这项研究的重点是评估这些前馈神经网络的输入活性表示。小脑颗粒细胞的活性通过平行纤维传递，并转化为Purkinje细胞活性。小脑皮层的唯一输出。在这种平行的纤维到Purkinje-Cell连接下的学习过程使每个Purkinje细胞对一组特定小脑状态敏感，这是在特定时间窗口中由颗粒细胞活性确定的。 Purkinje单元对每个神经输入状态都变得敏感，因此，网络作为能够通过监督学习的方式为每个提供的输入生成所需输出的功能。但是，由于网络自身的局限性（网络神经生物学基材固有的局限性），并非所有集合的Purkinje单元响应都可以分配给任何一组输入状态，也就是说，并非所有输入输出映射都可以学习。限制因素是通过颗粒细胞活性来表示输入状态。该表示形式的质量将确定网络学习各种输出的能力。在这项研究中，我们提出了一种算法，用于定量评估一组给定小脑状态之间根据其表示（颗粒细胞激活模式）之间的兼容性/干扰水平，而无需实际进行模拟和网络训练。该算法输入由一个实数矩阵组成，该矩阵将每个状态中每个考虑的颗粒细胞的活性水平编码。该表示形式的能力生成各种输出集，从几何评估，从而产生一个实际数字，以评估表示表示的好处
Supervised learning has long been attributed to several feed-forward neural circuits within the brain, with attention being paid to the cerebellar granular layer. The focus of this study is to evaluate the input activity representation of these feed-forward neural networks. The activity of cerebellar granule cells is conveyed by parallel fibers and translated into Purkinje cell activity; the sole output of the cerebellar cortex. The learning process at this parallel-fiber-to-Purkinje-cell connection makes each Purkinje cell sensitive to a set of specific cerebellar states, determined by the granule-cell activity during a certain time window. A Purkinje cell becomes sensitive to each neural input state and, consequently, the network operates as a function able to generate a desired output for each provided input by means of supervised learning. However, not all sets of Purkinje cell responses can be assigned to any set of input states due to the network's own limitations (inherent to the network neurobiological substrate), that is, not all input-output mapping can be learned. A limiting factor is the representation of the input states through granule-cell activity. The quality of this representation will determine the capacity of the network to learn a varied set of outputs. In this study we present an algorithm for evaluating quantitatively the level of compatibility/interference amongst a set of given cerebellar states according to their representation (granule-cell activation patterns) without the need for actually conducting simulations and network training. The algorithm input consists of a real-number matrix that codifies the activity level of every considered granule-cell in each state. The capability of this representation to generate a varied set of outputs is evaluated geometrically, thus resulting in a real number that assesses the goodness of the representation
