详情请进入 湖南阳光电子学校 已关注:人 咨询电话:0731-85579057 微信号:yp941688, yp94168
Kalman Normalization: Normalizing Internal Representations Across Network Layers
Part of: Advances in Neural Information Processing Systems 31 (NIPS 2018)
Authors Conference Event Type: Poster AbstractAs an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer. However, the effectiveness of BN would diminish with the scenario of micro-batch (e.g. less than 4 samples in a mini-batch), since the estimated statistics in a mini-batch are not reliable with insufficient samples. This limits BN's room in training larger models on segmentation, detection, and video-related problems, which require small batches constrained by memory consumption. In this paper, we present a novel normalization method, called Kalman Normalization (KN), for improving and accelerating the training of DNNs, particularly under the context of micro-batches. Specifically, unlike the existing solutions treating each hidden layer as an isolated system, KN treats all the layers in a network as a whole system, and estimates the statistics of a certain layer by considering the distributions of all its preceding layers, mimicking the merits of Kalman Filtering. On ResNet50 trained in ImageNet, KN has 3.4% lower error than its BN counterpart when using a batch size of 4; Even when using typical batch sizes, KN still maintains an advantage over BN while other BN variants suffer a performance degradation. Moreover, KN can be naturally generalized to many existing normalization variants to obtain gains, e.g. equipping Group Normalization with Group Kalman Normalization (GKN). KN can outperform BN and its variants for large scale object detection and segmentation task in COCO 2017.
Neural Information Processing Systems (NIPS)Papers published at the Neural Information Processing Systems Conference.
,新款本田佳御150,8000摩托车推荐,牛摩网官网网站,摩托迷官网,晚上骑机车视频,牛摩网官网网站,旧摩托车市场,摩托车锦标赛视频,摩托车跟轿车比赛视频,十大摩托跑车排行榜,赛摩比赛视频大全,2万左右的重机车,适合中年人的太子摩托车,适合中年人的太子摩托车,黄龙600报价参数,1万左右的摩托车跑车,1万入门级摩托车,进藏十大摩托,摩托车锦标赛视频,摩托,摩托跑车视频大全视频,世界公路摩托赛车视频,摩托跑车第一视角视频,摩托车夜间骑行视频,2019最好的合资踏板摩托车,摩托车夜间骑行视频,急卖125摩托车,深夜机车飙车视频,世界摩托车锦标赛官网,摩托车高速400飙车视频,2019年一万元左右踏板摩托车,3万元内街车,2万以内2019新款太子摩托车,二手买卖车,摩托车托运公司,大功率摩托车视频大全,2019入门级街车推荐,七八千的街车,豪爵铃木极客飒155,报废125摩托车多少钱,一万五左右的国产街车,无水印摩托车视频,大功率摩托车视频大全,2万左右的重机车,5000内街车,世界摩托车锦标赛官网,2万以内的街车,小太子摩托车报价,2019国内上市侉子摩托,适合中年人的太子摩托车,2万以内2019新款太子摩托车,二手125摩托车有人买吗,23万买什么机车好,龙嘉摩托车官方网,赛摩比赛视频大全,二手海王星摩托车转让,摩托车跑车商城,深夜机车飙车视频,雅马哈tzm150历史,旧摩托车市场。涟源市焊工培训学校,涟源市焊工培训班,涟源市焊工学校,涟源市学焊工的学校,涟源市焊工培训哪里好,涟源市焊工培训学校,涟源市焊工短期培训班,涟源市焊工培训学校地址,涟源市学焊工培训,涟源市焊工培训哪里好,涟源市焊工培训班,涟源市焊工技术培训.(编辑:hnygdzxx888)(整理:涟源市焊工培训学校)
湖南阳光电子学校教学特色