上一页 1 ··· 24 25 26 27 28 29 30 31 32 ··· 40 下一页

2015年11月11日

摘要: 目前看来,信号处理有自己的一些特性:1、一般低维2、一般要求实时性3、模型具有卷积或频域相乘,在加一个噪声,本身具有线性的特点4、数据在一般在时间轴上体现 阅读全文
posted @ 2015-11-11 17:09 一动不动的葱头 阅读(843) 评论(0) 推荐(0) 编辑

2015年11月7日

摘要: 阅读全文
posted @ 2015-11-07 17:11 一动不动的葱头 阅读(182) 评论(0) 推荐(0) 编辑
摘要: 参考文献:Multiple Object Tracking using K-Shortest Paths Optimization核心步骤:两步:一、detection 二、link detection该文工作:reformulating that step as a constrained flo... 阅读全文
posted @ 2015-11-07 17:04 一动不动的葱头 阅读(559) 评论(0) 推荐(0) 编辑

2015年11月6日

摘要: 直观地看:如果是softmax函数,我想有跟多的选择方向吧 阅读全文
posted @ 2015-11-06 21:38 一动不动的葱头 阅读(316) 评论(0) 推荐(0) 编辑
摘要: 参考文献imshow(K)直接显示K;imshow(K,[])显示K,并将K的最大值和最小值分别作为纯白(255)和纯黑(0),中间的K值映射为0到255之间的标准灰度值。 阅读全文
posted @ 2015-11-06 21:33 一动不动的葱头 阅读(289) 评论(0) 推荐(0) 编辑
摘要: idea:Concretely, for each example in the the labeled training datasetxl, we forward propagate the example through a convolutional and a pooling layer ... 阅读全文
posted @ 2015-11-06 21:31 一动不动的葱头 阅读(377) 评论(0) 推荐(0) 编辑
摘要: 参考文献:摘于上文献: The more general and powerful setting is theself-taught learningsetting, which does not assume that your unlabeled dataxuhas to be drawn ... 阅读全文
posted @ 2015-11-06 18:05 一动不动的葱头 阅读(298) 评论(0) 推荐(0) 编辑

2015年11月5日

摘要: 1 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 2 % 可调参数 3 %{ 4 test_path='C:\Users\co... 阅读全文
posted @ 2015-11-05 21:14 一动不动的葱头 阅读(213) 评论(0) 推荐(0) 编辑
摘要: 1 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 2 % 可调参数 3 %{ 4 test_path='C:\Users\co... 阅读全文
posted @ 2015-11-05 19:02 一动不动的葱头 阅读(227) 评论(0) 推荐(0) 编辑
摘要: 1 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 2 % 可调参数 3 %{ 4 test_path='C:\Users\co... 阅读全文
posted @ 2015-11-05 13:53 一动不动的葱头 阅读(153) 评论(0) 推荐(0) 编辑
上一页 1 ··· 24 25 26 27 28 29 30 31 32 ··· 40 下一页

导航