本人AI知识体系导航 - AI menu

• 如果能再给我一次机会，我会这么选课，韭菜不要多问为什么。

s1 
COMP9021 - Principles of Programming

COMP9417 - Machine Learning and Data Mining

COMP9814 - Extended Artificial Intelligence

GSOE9820 - Engineering Project Management

s2
COMP9024 - Data Structures and Algorithms

COMP6771 - Advanced C++ Programming

COMP9517 - Computer Vision

MATH5905 - Statistical Inference

s3
COMP9801 - Extended Design & Analysis of Algorithms

COMP9318 - Data Warehousing and Data Mining

COMP9319 - Web Data Compression and Search

MATH5960 - Bayesian inference and Computation

s4 
COMP9313 - Big Data Management

COMP9418 - Advanced Topics in Statistical Machine Learning

COMP9444 - Neural Networks

COMP9900 - Information Technology Project

 

• 如果能再给我一次机会，我会首选ThinkPad。

中端P系列，或者高端T系列。

 

 

 

Relevant Readable Links

 

Name	Interesting topic	Comment
Edwin Chen	非参贝叶斯
徐亦达老板	Dirichlet Process	学习目标：Dirichlet Process, HDP, HDP-HMM, IBP, CRM
Alex Kendall	Geometry and Uncertainty in Deep Learning for Computer Vision	语义分割
colah's blog	Feature Visualization
Jason Yosinski	Understanding Neural Networks Through Deep Visualization
田渊栋		general CV
alexisbcook	Global Average Pooling Layers for Object Localization	目标定位
Tombone	http://www.computervisionblog.com/	DL, CV and the algorithms that are shaping the future of AI.

  

Others：

http://www.cnblogs.com/tornadomeet/archive/2012/06/24/2560261.html【理论总结挺好】 

http://www.cnblogs.com/charlotte77/【统计机器学习，可能实用】

http://blog.csdn.net/zhangjunhit/article/list/1【论文阅读笔记不错】

 

 

专注于数据分析之Kaggle and 图像处理之AR on phone

 

---

 

How to be a Top AR Full-Stack Developer

 

正如该链接中所言，学习了哪些知识，计算机视觉才算入门？

计算机视觉涉及面甚广，找到一类问题好好研究并实践就好，这类问题在本博客就指AR问题。

Ref: 计算机视觉入门书？

 

列出现代计算机视觉体系的主要科目（知识点）及其递进关系。

一个单元代表一门course (12 weeks)或者一本book (600 pages)的学习量，亲测。

循序渐进很重要，后辈务必去掉大跃进的念头。

人工智能之计算机视觉 - 学术体系
第四层	计算机视觉：模型，学习，推理
第三层	统计机器学习		深度学习
第二层	机器学习入门		计算机视觉入门
第一层	统计推断	贝叶斯分析	多元线性分析	凸优化

 

编程是基本功，无须赘述。

人工智能之计算机视觉 - 软件工程
第四层	实践！实践！实践！
第三层	Android API, RN, OpenCV, Scikit-learning, ARToolkit, Unity
第二层	软件架构，设计模式，代码管理，单元测试
第一层	C/C++, Python, Java, Kotlin, Javascript, SQL

 

如上，乃基本的学习路线，仅是参考，仍可细分，但基本上具备了AR全栈开发者的潜力。

 

Phones with ARCore support, Feb, 2018

Indoor navigation app: you'll never be lost again

Inside Navigation【好东西，但时机不对】

 

---

 

My Hierarchy of AI Knowledge

实践阶段

如果你想要一个能走到冰箱面前而不撞到墙壁的机器人，那就使用 SLAM。

如果你想要一个能识别冰箱中各种物品的机器人，那就使用 Deep Learning。

基本上，这算一个风口；仅指路，不领路，需深耕。

 

增强现实 - Deep Learning 识别

综述：

[Object Tracking] Overview of Object Tracking

[Object Tracking] Overview of algorithms for Object Tracking

 

轮廓识别：

[Object Tracking] Active contour model - Snake Model

[Object Tracking] Deep Boundary detection Tech

[Object Tracking] Contour Detection through Tensorflow running on smartphone

[Object Tracking] Contour Detection through OpenCV

 

目标定位：

[OpenCV] Real-time object detection with dnn module in OpenCV 3.3

[Localization] SSD - Single Shot MultiBoxDetector

[Localization] MobileNet with SSD

[Tensorflow] Android Meets TF in TensorFlow Dev Summit 2017

 

[Tensorflow] Object Detection API - prepare your training data

[Tensorflow] Object Detection API - build your training environment

[Tensorflow] Object Detection API - predict through your exclusive model

[Tensorflow] Object Detection API - retrain mobileNet

[Tensorflow] Object Detection API - mobileNet_v1.py

 

[Object Tracking] Identify and Track Specific Object

[Object Tracking] MeanShift

 

增强现实 - SLAM 跟踪

[SLAM] 01. "Simultaneous Localization and Mapping"

[SLAM] 02. Some basic algorithms of 3D reconstruction

[SLAM] 03. ORB-SLAM2

[SLAM] AR Tracking based on which tools?

[ARCORE, Continue...]

 

 

 

冲刺阶段

已看到收敛趋势，查缺补漏，攻克难点疑点。

融会贯通方可运用自如，解决新问题。

  

生成式网络 - Conv & Deconv

[Paper] Before GAN: sparse coding

Continue... 

 

深度学习概念 - UFLDL

[UFLDL] Basic Concept

[UFLDL] Linear Regression & Classification

[UFLDL] Dimensionality Reduction

[UFLDL] Generative Model

[UFLDL] Sparse Representation

[UFLDL] ConvNet

[UFLDL] Train and Optimize

 

深度学习理论 - Stats 385

[Stats385] Lecture 01-02, warm up with some questions

[Stats385] Lecture 03, Harmonic Analysis of Deep CNN

[Stats385] Lecture 04: Convnets from Probabilistic Perspective

[Stats385] Lecture 05: Avoid the curse of dimensionality

【暂时不实用，点到为止】

 

统计机器学习 - PRML

9. [Bayesian] “我是bayesian我怕谁”系列 - Gaussian Process

8. [Bayesian] “我是bayesian我怕谁”系列 - Variational Autoencoders

7. [Bayesian] “我是bayesian我怕谁”系列 - Boltzmann Distribution

6. [Bayesian] “我是bayesian我怕谁”系列 - Markov and Hidden Markov Models

5. [Bayesian] “我是bayesian我怕谁”系列 - Continuous Latent Variables

4. [Bayesian] “我是bayesian我怕谁”系列 - Variational Inference

3. [Bayesian] “我是bayesian我怕谁”系列 - Latent Variables

2. [Bayesian] “我是bayesian我怕谁”系列 - Exact Inference

1. [Bayesian] “我是bayesian我怕谁”系列 - Naive Bayes with Prior

  

 

  

混沌阶段

打地基，处于强化学习初期的不稳定阶段，感谢马尔科夫收敛的性质，目标已收敛；自下向上，基本遵循循序渐进的学习过程，夯实知识体系。

了解领域内的疑难点，认识技术细节的价值，为下一阶段做准备。

内容多为早年整理，倾向于参考价值。

 

Bayesian Analysis

R与采样方法：

[Bayes] What is Sampling

[Bayes] Point --> Line: Estimate "π" by R

[Bayes] Point --> Hist: Estimate "π" by R

[Bayes] qgamma & rgamma: Central Credible Interval

[Bayes] Hist & line: Reject Sampling and Importance Sampling

[Bayes] runif: Inversion Sampling

[Bayes] dchisq: Metropolis-Hastings Algorithm

[Bayes] prod: M-H: Independence Sampler for Posterior Sampling

[Bayes] Metroplis Algorithm --> Gibbs Sampling

[Bayes] Parameter estimation by Sampling

[Bayes] openBUGS: this is not the annoying bugs in programming

 

PGM基础：

[PGM] What is Probabalistic Graphical Models

[PGM] Bayes Network and Conditional Independence

[PGM] Temporal Models

[PGM] Markov Networks

[PGM] Variable elimination and Belief propagation

[PGM] Exact Inference for calculating marginal distribution

 

贝叶斯基础：

[BOOK] Applied Math and Machine Learning Basics

[Bayes] Multinomials and Dirichlet distribution

[Bayes] Understanding Bayes: A Look at the Likelihood

[Bayes] Understanding Bayes: Updating priors via the likelihood

[Bayes] Understanding Bayes: Visualization of the Bayes Factor

[Bayes] Why we prefer Gaussian Distribution

[Bayes] Improve HMM step by step

[Math] Unconstrained & Constrained Optimization

[Bayes] KL Divergence & Evidence Lower Bound

[Bayes] Variational Inference for Bayesian GMMs

[Bayes] Latent Gaussian Process Models

 

学习指南： 

[Math] A love of late toward Mathematics - how to learn it?

[Bayes ML] This is Bayesian Machine Learning 【原文总结得相当好】

 

 

Deep Learning

理论：

[BOOK] Applied Math and Machine Learning Basics             【DL书基础，1至5章笔记】

[Hinton] Neural Networks for Machine Learning - Basic

[Hinton] Neural Networks for Machine Learning - Converage

[Hinton] Neural Networks for Machine Learning - RNN

[Hinton] Neural Networks for Machine Learning - Bayesian

[Hinton] Neural Networks for Machine Learning - Hopfield Nets and Boltzmann Machine

 

编程：

[Tensorflow] Architecture - Computational Graphs   【TF 框架】 

[Tensorflow] Practice - The Tensorflow Way     　　【相对基础】

[Tensorflow] Cookbook - The Tensorflow Way 　　【前者的 Detail】

[Tensorflow] Cookbook - Neural Network         　　【代码基础写法】

[Tensorflow] Cookbook - CNN                          　　【卷积网络专题】

[Tensorflow] Cookbook - Object Classification based on CIFAR-10

[Tensorflow] Cookbook - Retraining Existing CNNs models - Inception Model

 

[Tensorflow] RNN - 01. Spam Prediction with BasicRNNCell

[Tensorflow] RNN - 02. Movie Review Sentiment Prediction with LSTM

[Tensorflow] RNN - 03. MultiRNNCell for Digit Prediction

[Tensorflow] RNN - 04. Work with CNN for Text Classification

 

[TensorBoard] Cookbook - Tensorboard

[TensorBoard] Train and Test accuracy simultaneous tracking

[TensorBoard] Name & Variable scope

 

训练：

[Converge] Gradient Descent - Several solvers

[Converge] Weight Initialiser

[Converge] Backpropagation Algorithm 【BP实现细节】

[Converge] Feature Selection in training of Deep Learning 【特性相关性的影响】

[Converge] Training Neural Networks 【cs231n-lec5&6，推荐】

[Converge] Batch Normalisation

 

卷积：

[CNN] What is Convolutional Neural Network 【导论】

[CNN] Understanding Convolution 【图像角度理解】

[CNN] Tool - Deep Visualization

 

模型：

[Model] LeNet-5 by Keras

[Model] AlexNet

[Model] VGG16

[Model] GoogLeNet

[Model] ResNet　　

[Localization] R-CNN series for Localization and Detection

[Localization] YOLO: Real-Time Object Detection

[Localization] SSD - Single Shot MultiBoxDetector

[Localization] MobileNet with SSD

 

其他：

[GPU] CUDA for Deep Learning, why?

[GPU] DIY for Deep Learning Workstation

[Keras] Install and environment setting

[Keras] Develop Neural Network With Keras Step-By-Step 

[GAN] *What is Generative networks 【导论，”生成式模型“有哪些，与”判别式模型“同级】

[GAN] How to use GAN - Meow Generator 

[DQN] What is Deep Reinforcement Learning 【导论：此方向优先级低】

[Understanding] Compressive Sensing and Deep Model 【感知压缩，暂且不懂】

[DL] *Deep Learning for Industry - Wang Yi 【课外阅读】

  

 

Machine Learning

  

/* ML文件夹待整理 */

 

 

IR & NLP基础

检索：

[IR] Boolean retrieval

[IR] Index Construction

[IR] Compression

[IR] Tolerant Retrieval & Spelling Correction & Language Model

[IR] Probabilistic Model

[IR] Link Analysis

[IR] Ranking - top k

[IR] Evaluation

[IR] Information Extraction

[IR] Open Source Search Engines

[IR] Search Server - Sphinx

[IR] Concept Search and LSI

[IR] Concept Search and PLSA

[IR] Concept Search and LDA

 

压缩：

[IR] What is XML

[IR] XML Compression

[IR] Advanced XML Compression - ISX

[IR] Advanced XML Compression - XBW

[IR] XPath for Search Query

[IR] Graph Compression

[IR] Bigtable: A Distributed Storage System for Semi-Structured Data

[IR] Huffman Coding

[IR] Arithmetic Coding

[IR] Dictionary Coding

[IR] BWT+MTF+AC

[IR] String Matching

[IR] Suffix Trees and Suffix Arrays

[IR] Time and Space Efficiencies Analysis of Full-Text Index Techniques

[IR] Extraction-based Text Summarization

 

其他：

[IR] Word Embeddings

 

【以上内容需随recommended system一起再过一遍，完善体系】 

 

 

AR基础

[Artoolkit] Marker Training

[Artoolkit] ARToolKit's SDK Structure on Android

[Artoolkit] Framework Analysis of nftSimple

[Artoolkit] kpmMatching & Tracking of nftSimple

[Artoolkit] Android Sample of nftSimple

[Artoolkit] Can I Use LGPL code for commercial application

[Artoolkit] Marker of nftSimple

[Artoolkit] ARSimpleNativeCarsProj for Multi Markers Tracking

 

[Unity3D] 01 - Try Unity3D

[Unity3D] 02 - ** Editor Scripting, Community Posts, Project Architecture

[Unity3D] 03 - Component of UI

[Unity3D] 04 - Event Manager

[Unity3D] 05 - Access to DB or AWS

【简单涉及3D建模知识点，非重点】

 

　　  

CV基础

概念：

[OpenCV] Install openCV in Qt Creator

[OpenCV] Basic data types - Matrix

[OpenCV] IplImage and Operation

[OpenCV] HighGUI

[OpenCV] Image Processing - Image Elementary Knowledge

[OpenCV] Image Processing - Grayscale Transform

[OpenCV] Image Processing - Frequency Domain Filtering

[OpenCV] Image Processing - Spatial Filtering

[OpenCV] Image Processing - Fuzzy Set

[OpenCV] Feature Extraction

[OpenCV] Feature Matching

[SLAM] Little about SLAM

[SLAM] Camera math knowledge

[Tango] Basic Knowledge

 

实践：

// 内容将合并，重新整理

[OpenCV] Samples 01: drawing【几何图案、文字等】

[OpenCV] Samples 02: [ML] kmeans【聚类算法】

[OpenCV] Samples 03: cout_mat【Mat计算能力】

[OpenCV] Samples 04: contours2【二值图案找轮廓】

[OpenCV] Samples 05: convexhull【散点的凸包轮廓】

[OpenCV] Samples 06: [ML] logistic regression【线性二分类】

[OpenCV] Samples 07: create_mask【鼠标圈图】

[OpenCV] Samples 08: edge【边缘检测】

[OpenCV] Samples 09: plImage <==> Mat 【色域通道分离】

[OpenCV] Samples 10: imagelist_creator【图片地址list参数】

[OpenCV] Samples 11: image sequence【视频流提取】

[OpenCV] Samples 12: laplace【视频流处理】

[OpenCV] Samples 13: opencv_version【版本信息显示】

[OpenCV] Samples 14: kalman filter【预测下一个状态】

[OpenCV] Samples 15: Background Subtraction and Gaussian mixture models【背景差分】

[OpenCV] Samples 16: Decompose and Analyse RGB channels【色域通道分离】

[OpenCV] Samples 17: Floodfill【聚类算法】

[OpenCV] Samples 18: Load image and check its attributes【图片属性】

 

扩展： 

[CNN] Face Detection

[Android Studio] Using Java to call OpenCV

[Android Studio] Using NDK to call OpenCV

[OpenCV] Install OpenCV 3.3 with DNN

[OpenCV] Install OpenCV 3.4 with DNN

 

趣码收集：

[Link] Face Swap Collection 

[Link] Face Swap without DLIB【代码可用】

 

  

算法基础

[Algorithm] Deferred Acceptance Algorithm

[Algorithm] Beating the Binary Search algorithm – Interpolation Search, Galloping Search

[Algorithm] Warm-up puzzles

[Algorithm] Asymptotic Growth Rate

[Algorithm] Polynomial and FFT

[Algorithm] Maximum Flow

[Algorithm] String Matching and Hashing

[Optimization] Greedy method

[Optimization] Dynamic programming

[Optimization] Advanced Dynamic programming

  

---

Everything here starts from 2016