RiKler的博客

Introduction to Neural NetworksComputational graphsBackPropagation - A method to compute the gradients of abitrarily complex functionA recursive application of Chain ruleWe get the gradient backprop from the front and comupte with the local gradi

Loss Functions and OptimizationPreview the Goal in this lectureDefine a loss functionCome up with a way of finding the paras that minimize the (1)(optimization)The Remain Problem from last lectureHow to choose the W para ?[外链图片转存失败,源站可能有防盗链机制,建

Image ClassificationThis is my note to the course CS231n Stanford Convolutional Neural NetworkComputer’ WorkInput an image, and assign one of the label amoung the given labels.The Problem:Semantic GapViewpoint variationilluminationDeformationO