摘要: spike 阅读全文
posted @ 2017-09-19 20:33 papering 阅读(179) 评论(0) 推荐(0)
摘要: @Matthew 【[抱拳]】推荐系统中,传统的两大算法,无论是基于人的过滤,还是基于物品的过滤,在前期历史数据的量和质都不充足的情况下,这两种传统的算法都无法冷启动。 【基于ANN的一种解决办法】 张三第一次点击了汽车广告,通过ANN训练,使得输出层的汽车的概率最大,次之的就为接下来要投出的广告类 阅读全文
posted @ 2017-09-19 20:28 papering 阅读(224) 评论(0) 推荐(0)
摘要: BLEU is designed to approximate human judgement at a corpus level, and performs badly if used to evaluate the quality of individual sentences. https:/ 阅读全文
posted @ 2017-09-19 18:36 papering 阅读(227) 评论(0) 推荐(0)
摘要: 安装TensorFlow 包依赖 https://www.tensorflow.org/tutorials/layers Building the CNN MNIST Classifier 【Each of these methods accepts a tensor as input and re 阅读全文
posted @ 2017-09-19 18:10 papering 阅读(507) 评论(0) 推荐(0)
摘要: http://mathworld.wolfram.com/HadamardProduct.html 阅读全文
posted @ 2017-09-19 16:21 papering 阅读(231) 评论(0) 推荐(0)
摘要: Hermitian_function 阅读全文
posted @ 2017-09-19 15:13 papering 阅读(129) 评论(0) 推荐(0)
摘要: Logistic function hyperbolic tangent arctangent function Gudermannian function Error function Generalised logistic function Smoothstep function Specif 阅读全文
posted @ 2017-09-19 14:27 papering 阅读(606) 评论(0) 推荐(0)
摘要: zh.wikipedia.org/wiki/卷积神经网络 池化(Pooling)是卷积神经网络中另一个重要的概念,它实际上一种形式的向下采样。有多种不同形式的非线性池化函数,而其中“最大池化(Max pooling)”是最为常见的。它是将输入的图像划分为若干个矩形区域,对每个子区域输出最大值。直觉上 阅读全文
posted @ 2017-09-19 14:21 papering 阅读(279) 评论(0) 推荐(0)
摘要: https://en.wikipedia.org/wiki/Convolutional_neural_network Convolutional layers apply a convolution operation to the input, passing the result to the 阅读全文
posted @ 2017-09-19 14:15 papering 阅读(229) 评论(0) 推荐(0)
摘要: Convolutional networks may include local or global pooling layers[clarification needed], which combine the outputs of neuron clusters at one layer int 阅读全文
posted @ 2017-09-19 11:19 papering 阅读(214) 评论(0) 推荐(0)