主页

LSTM + CNN Introduction Solution Why sigmoid? Sigmoid function is 0 - 1 layout, it could be used to remember or forget something. Why tanh We want to avoid vanishing gradient problem. The second derivative of tanh is mo

Basic Knowledge 声明 短变量声明只能在函数内部使用 package main // myvar := 1 // false var myvar = 1 // right func main() { } 不能使用nil初始化未指定类型的变量 var x = nil // false var x interface{} = nil // right _ = x 字符串没有nil var x string if x == nil { // err } if x == "" { x = "default" } Slice & Array 首先Slice和Array是有区别的，Slice是指针，而Array已经预...

One-Hot Encoding Key word: Encoding Label Encoding | Food Name | Categorical | Calories | | — | — | — | | Apple | 1 | 95 | | Chicken | 2 | 231 | | Broccoli | 3 | 50 | One-hot encoding Apple Chicken Broccoli Calories 1 0 0 95 0 1 0 ...

ESMM Advantage: Combine two nn together with by a dot product finally. Key word: DNN Usage: Predict CVR and CTR Predicting post-click conversion rate is the problem they try to solve. Why the Problem Is Difficult Current method has two problems, one is illustrated as the following. Sample selection bias problem means that the traini...

Wide&Deep Advantage: 记忆和泛化能力的高度结合。 Key word: DNN, Generalization, Regressor Usage: 用于推荐，结合线性模型的记忆能力，和不需要做出很好的特征工程就能拥有强大泛化能力的DNN模型，来达到更加精准的预测效果 Motivation Categorial data using one-hot encoding representation could memorize a feature pair that correlates with the target label. But this requires feature engineering. DNNs could learn low-di...

Logistic Regression Advantage: Use logistic function Usage: Used to predict classification problems Introduction Logistic regression is used to predict classification result Details Suppose we try to predict whether an email is spam, we have attributes $x_1, x_2, … x_n$ for prediction. We define a function $z = \theta_0 + \theta_1x_1 + \th...

DSMM Advantage: Use DNN models to do this. Key word: DNN Usage: Used in text-based query-to-document retrieval. Objective Retrieve documents related with an input query. Proposed DNN architecture: Term vector Term vector use letter or word as a dimension and counts of that term. Word hashing In order to reduce the dimensionality of bag...

Cross-entropy loss Usage: Optimize classifier. Main idea: It measures the distance between predicted output probability distribution and actual probability distribution. https://gombru.github.io/2018/05/23/cross_entropy_loss/