标题： GINN：神经网络的几何图示 显示英文标题

标题： GINN: Geometric Illustration of Neural Networks

摘要： 本非正式技术报告详细介绍了三层全连接神经网络中ReLU单元的决策边界几何图示。该网络被设计并训练以根据(x, y)输入位置预测像素强度。构建了神经网络的几何图示工具（GINN）以可视化和追踪神经网络训练过程中ReLU单元从激活变为关闭（反之亦然）的点。文中讨论了几种观察到的现象。此技术报告是博客文章及其在线演示的辅助文档，可在http://www.bayeswatch.com/2018/09/17/GINN/获取。 显示英文摘要

摘要： This informal technical report details the geometric illustration of decision boundaries for ReLU units in a three layer fully connected neural network. The network is designed and trained to predict pixel intensity from an (x, y) input location. The Geometric Illustration of Neural Networks (GINN) tool was built to visualise and track the points at which ReLU units switch from being active to off (or vice versa) as the network undergoes training. Several phenomenon were observed and are discussed herein. This technical report is a supporting document to the blog post with online demos and is available at http://www.bayeswatch.com/2018/09/17/GINN/.