zxggghjju的博客

原创 python多进程

原创 Clustering by Passing Messages Between Data Points【论文翻译】

Clustering by Passing Messages Between Data PointsBrendan J. Frey* and Delbert DueckClustering data by identifying a subset of representative examples is important for processing sensory signals and detecting patterns in data. Such “exemplars” can be fou

原创 Reducing the Dimensionality of Data with Neural Networks【论文翻译】

Reducing the Dimensionality of Data with Neural Networks利用神经网络降低数据的维度G. E. Hinton* and R. R. SalakhutdinovHigh-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct h

原创 Nonlinear Dimensionality Reduction by Locally Linear Embedding[论文翻译]

Nonlinear Dimensionality Reduction by Locally Linear EmbeddingSam T. Roweis 1 and Lawrence K. Saul2Many areas of science depend on exploratory data analysis and visualization.The need to analyze large amounts of multivariate data raises the fundamental p

原创 Deep Residual Learning for Image Recognition【论文翻译】

DeepResidualLearningforImageRecognitionKaiming He & Xiangyu Zhang & Shaoqing Ren & Jian SunAbstractDeeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substant

原创 A Global Geometric Framework for Nonlinear Dimensionality Reduction [论文翻译]

论文题目：A Global Geometric Framework for Nonlinear Dimensionality Reduction论文来源:Science 290, 2319 (2000);翻译人：BDML@CQUT实验室A Global Geometric Framework for Nonlinear Dimensionality Reduction非线性降维的全局几何框架Joshua B. Tenenbaum,1* Vin de Silva,2 John C. Langford

原创 常见的希腊字母及读音

1、Αbai α alpha a:lf 阿尔法2、Β β beta bet 贝塔du3、Γ γ gamma ga:m 伽马4、Δ δ delta delt 德尔塔5、Ε ε epsilon ep silon 伊普西龙6、Ζ ζ zeta zat 截塔zhi7、Ηdao η eta eit 艾塔8、Θ θ theta θit 西塔9、Ι ι iota aiot 约塔10、Κ κ kappa kap 卡帕11、∧ λ lambda lambd 兰布达12、Μ μ mu mju 缪13、Ν

原创 Deep learning(Yann LeCun, Yoshua Bengio & Geoffrey Hinton) 英汉双语

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the in speech recognition, visual object recognition, o

原创 python装饰器

什么是装饰器：装饰器本质上是一个Python函数，它可以让其他函数在不需要做任何代码变动的前提下增加额外功能，装饰器的返回值也是一个函数对象。 它经常用于有切面需求的场景，比如：插入日志、性能测试、事务处理、缓存、权限校验等场景。案列：现在有一个购买功能，但购买之前需要用户登录后才能购买商品，需要在不修改源代码的情况下实现此功能def buy(): print("购买商品")使用装饰器：def login(fun): def inner(): print("校验完