原创 [NOTE in progress] Simulation Optimization
簡單記錄一下關於仿真優化的一些知識點和思考。主要基於:Handbook of Simulation Optimization, Michael Fu Table of Contents Overview Discrete Optimiza
原创 A Road Map for Deep Learning
點這個: https://towardsdatascience.com/a-road-map-for-deep-learning-b9aee0b2919f
原创 Stochastic Optimization: Casual Notes
Currently learning stochastic optimization (SO) theory, I will note important content here. Some book references ar
原创 Graph Neural Network: A First Glance
@[TOC]GNN Resources 從圖(Graph)到圖卷積(Graph Convolution):漫談圖神經網絡模型 (一) Vocabulary Fixed Point Theorem : a convergency
原创 Git 項目管理流程與協作方式
近期隨着團隊規模的擴大以及業務需求的逐漸增長,我花時間思考了團隊的代碼協作方式,過程中有些收穫跟大家分享一下。 首先推薦幾篇文章: 阮一峯的博客介紹了比較主流的集中Git工作流程,再加上這裏提到的SVN時代的單主幹模型,大家應該有
原创 [NOTE in progress] Distributed Optimization and Statistical Learning via ADMM - Boyd
Reading notes of the paper "Distributed Optimization and Statistical Learning via ADMM" by Boyd, Parikh, Chu, Peleato a
原创 [NOTE in progress] ECE236C - Optimization Methods for Large-Scale Systems [on going]
Source:http://www.seas.ucla.edu/~vandenbe/ee236c.html Introduction Outline First-order algorithms Decomposition and s
原创 An Overview of Reinforcement Learning
強化學習概覽 This overview is largely based on this article: https://medium.com/@SmartLabAI/reinforcement-learning-algorithms
原创 【轉】MCMC採樣詳解
Check here:https://zhuanlan.zhihu.com/p/37121528
原创 【轉載】Overview of gradient descent algorithms
Overview of gradient descent algorithms An overview of gradient descent optimization algorithms Gradient descent is
原创 [NOTE] Distributed Optimization and Statistical Learning via ADMM - Boyd
Reading notes of the paper "Distributed Optimization and Statistical Learning via ADMM" by Boyd, Parikh, Chu, Peleato a
原创 Taylor, Jacobian, Hessian, Newton and all the else about gradient
本文的主要目的是對基於gradient的一些approximation知識點以及優化方法做一個簡單的review。詳細內容參考引用鏈接,這裏只列出key points,主要是在遺忘的時候能夠快速catch up… Jacobian矩陣和H
原创 Benders Decomposition vs Danzig-Wolf Decomposition
本文記錄了一些對Benders (B)和 Danzig-Wolf(DW) decomposition 的一些初步理解以及兩者的使用場景與對比。 來源: Jacek Gondzio, https://www.researchgate.net
原创 一些Java編程規約
使用java.util.Objects類中的方法進行對象間操作,如equals。這樣可以避免空引用的異常。 Integer i=... 在128~-127之間的值來自於cache。這一範圍是可更改的。然而Long類型的這一範圍是不可更改的
原创 Brief Intro of Deep Learning【李宏毅課程筆記-待完成】
李宏毅 2006, Restricted Boltzmann Machine. Complex. Used to initialize multi-layer perceptron (1980), to be called De