QA Official

Why should linear regression loss function be in square form

https://qaofficial.com/post/2019/04/04/68785-why-should-linear-regression-loss-function-be-in-square-form.html 2019-04-04
We learned in the previous " Linear Regression" that for training data samples (xi,yi)({x_i},{y_i}), we have the following fitting straight line: {\widehat y_i} = {\theta _0} + {\theta _1} \bullet {x_i} We constructed a loss function: C = \sum\limits_{i = 1}^n {{{({y_i} - {{\widehat y}_i})}^2}} Indicates the sum of squares of the vertical distances from each training data point (xi,yi)({x_i},{y_i}) to the fitting straight line yi = θ 0+θ 1Xi { \ wide hat y _ I } = { \ theta _ 0 }+{ \ theta _ 1 } \ bullet { x _ I }.

[ Reprint Forbidden ] Geometric Analysis of Karush-Kuhn-Tucker(KKT) Conditions

https://qaofficial.com/post/2019/04/04/68810-reprint-forbidden-geometric-analysis-of-karush-kuhn-tuckerkkt-conditions.html 2019-04-04
Write in front Karush-Kuhn-Tucker (KKT) condition is an important idea in optimization to solve Lagrange duality problems, and is widely used in operations research, convex and non-convex optimization, machine learning and other fields.In this blog, I try to explain Lagrange duality problem and understanding of KKT condition from the perspective of geometry.If you want to learn more about Convex Optimization, it is recommended that Stanford CS229 and Stephen Boyd's classic

[ machine learning ] k means algorithm python implementation

https://qaofficial.com/post/2019/04/04/68831-machine-learning-k-means-algorithm-python-implementation.html 2019-04-04
After taking Stanford Andrew NG class and finishing all the exercises with matlab, I felt that I was still not satisfied. Therefore, I decided to use pyton to implement the algorithm in class one by one to deepen my understanding, and at the same time, I also avoided becoming a package adjuster. Ha ha, without saying much, I got to the point. Kmeans is a classical unsupervised clustering algorithm, and its content is easy to understand.

a simple word2vec implementation

https://qaofficial.com/post/2019/04/04/68854-a-simple-word2vec-implementation.html 2019-04-04
Recently I learned word2vec and realized a simple word2vec implementation according to my own understanding. The algorithm has a total of three data structures, an input layer, an embedding_lookup layer and an output layer. The simple code is as follows: import tensorflow as tf import numpy as np contents = '一二三四五六七八九十一二三四五六七八九

understanding of springioc mechanism

https://qaofficial.com/post/2019/04/04/110526-understanding-of-springioc-mechanism.html 2019-04-04
Recently I saw a blog post about spring's IOC mechanism, which is well understood.However, the original author did not give too many explanations on the positioning of resources, the analysis of resources and the loading strategy of resources in the spring bottom layer, which will be added later. IOC(DI): In fact, the concept at the core of the Spring architecture is not so complicated, much less obscure as some books describe.

1.3.1Netty QuickStart

https://qaofficial.com/post/2019/04/03/68715-1.3.1netty-quickstart.html 2019-04-03
Netty QuickStart The following enumerates the basic building blocks of all Netty applications, including clients and servers. BOOTSTRAP Netty applications start by setting the bootstrap class, which provides a container for application network layer configuration. CHANNEL The underlying network transport API must provide interfaces for application I/O operations, such as reading, writing, connecting, binding, etc.For us, this is a structure that almost always becomes a "

BN layer LN layer WN layer function introduction

https://qaofficial.com/post/2019/04/03/68650-bn-layer-ln-layer-wn-layer-function-introduction.html 2019-04-03
1: BN layer Li Hongyi Video Explanation bn (batch normalization) layer (1) Accelerating convergence (2) Controlling over-fitting, which can reduce the insensitivity of the network to initialization weights with little or no Dropout and regularization (3) and allow a larger learning rate to be used.

Cat VS Dog maximum independent set

https://qaofficial.com/post/2019/04/03/68677-cat-vs-dog-maximum-independent-set.html 2019-04-03
The zoo have N cats and M dogs, today there are P children visiting the zoo, each child has a like-animal and a dislike-animal, if the child’s like-animal is a cat, then his/hers dislike-animal must be a dog, and vice versa. Now the zoo administrator is removing some animals, if one child’s like-animal is not removed and his/hers

NO 2 Convolution Neural Network

https://qaofficial.com/post/2019/04/03/68586-no-2-convolution-neural-network.html 2019-04-03
Convolutional Neural Network, CNN for short. Main knowledge points: 1) The main idea of 1)CNN 2)CNN's Forward Conduction Algorithm 3) Implementation and Visualization of 3)CNN 1. CNN's Main Ideas CNN's main ideas can be summarized as two points: Sparse Connectivity and Shared Weights Convolution neural network (CNN) is an extension of neural network (NN). CNN differs from NN mainly in the following two points: 1) Different input forms are received

Netty Getting Started

https://qaofficial.com/post/2019/04/03/68730-netty-getting-started.html 2019-04-03
1, introduction Java1.4 provides NIO to enable developers to write high-performance server-side programs using Java, but using the native NIO API is like network programming in Linux C, and still requires low-level work such as IO processing and protocol processing.Therefore, just as C server-side programs use libevent as a network application framework, NIO-based network application frameworks are emerging in the Java community.Among them, Netty produced by Jboss is the best.