Build an Artificial Neural Network from scratch to predict Coronavirus infection

https://medium.com/@ngocson2vn/build-an-artificial-neural-network-from-scratch-to-predict-coronavirus-infection-8948c64cbc32

https://github.com/ngocson2vn/NeuralNetworks/tree/master/ann

A gentle explanation of Backpropagation in Convolutional Neural Network (CNN)

https://medium.com/@ngocson2vn/a-gentle-explanation-of-backpropagation-in-convolutional-neural-network-cnn-1a70abff508b

https://github.com/ngocson2vn/NeuralNetworks/tree/master/cnn

MIT 學者利用 AI 發現超強抗生素，成果登《Cell》雜誌封面

https://technews.tw/2020/02/25/artificial-intelligence-yields-new-antibiotic/?fbclid=IwAR1UBZvz5xGyVv-DonIlf9DNc0hLx1fDY10P9UuGSzxY5wSxMSf4atnpwG8

COCO-GAN: Generation by Parts via Conditional Coordinating

https://hubert0527.github.io/COCO-GAN/?fbclid=IwAR3rLHb95RCSOf7hjg1XUnpArlOYa8Q56DlWetrwxWzyWuLb7584Je3BLuI

Python iterator and generator

要成為迭代器，首先必須建立一個 __iter__ method告訴編譯器說這個類別是一個迭代器，每次進行迭代時都會呼叫這個method，然後回傳給自己(self)。接著還要建立一個__next__ method好讓外部可以透過內建函式next()去告訴迭代器說要產生下一個元素。

產生器可以透過函式利用yield指令或者tuple的comprehension來產生一系列數字，透過in或者next()可以把產生器裡面的元素產生出來

結論是產生器只能一次產生所有元素，比較適合存放容量小的元素，迭代器可以不斷產生元素，比較適合產生大量的元素

最後無聊寫了一個綜合版本

參考
https://anandology.com/python-practice-book/iterators.html

Efficient Graph Generation with Graph Recurrent Attention Networks

https://arxiv.org/pdf/1910.00760.pdf
https://github.com/lrjconan/GRAN?fbclid=IwAR0lFLzqg7RDOVwG1L5DPQCYwETMh1Grh5f5qYmhWxhRy7ck19kbM6sGiQ4

Cosine Similarity – Understanding the math and how it works (with python codes)

https://www.machinelearningplus.com/nlp/cosine-similarity/?fbclid=IwAR0yMv5xtRVCbGrh_JlCS5dlT4dNCWnWCatqigBdpHpDab3p827Xko0nDIU

What is convolution? A brief explanation.

https://www.neurozo-innovation.com/post/what-is-convolution

適合 RNA-seq 分析初學者的入門文章

https://www.ncbi.nlm.nih.gov/pubmed/29624415?fbclid=IwAR3-hMQ7UkpR4PTrtosU-rULhacwIo3CtRg2RP6nZv-PBfdpRV-AfVBpicw

Top 4 libraries you must know before diving into any deep learning projects

https://medium.com/@abhisheksingh007226/top-4-libraries-you-must-know-before-diving-into-any-deep-learning-projects-61904286478d

Neural Networks: Feedforward and Backpropagation Explained & Optimization

https://mlfromscratch.com/neural-networks-explained/?fbclid=IwAR1bgSK2jkbA6b3eez4rn6bWDIUA1yrKG8wnC8_yaDDl_Oy0iC0GgeGDpwY#/

入門圖深度學習

https://bangqu.com/87HN36.html?fbclid=IwAR3fNgbgI9UisDm0DkMSoraC5XXiU4g3ErrchdX0iP1GJabUOYTSxBxQ6Ts

Introduction to Applied Linear Algebra – Vectors, Matrices, and Least Squares

https://web.stanford.edu/~boyd/vmls/?fbclid=IwAR26avC7mPcJjrHr9vUyE2ScbEzZ-GIBmgS5nlF26G80VcVGIngItftqAO4

Bias-Variance Tradeoff in Machine Learning models

https://sameen.dev/ml/2020/02/11/Bias-variance-tradeoff.html?fbclid=IwAR3K3ba-aEj_RrBsa7yPkabjlQvDgnj9bzaWseY7Ija9Oc9OtJZrWoGGxjw

Awesome Graph Classification

https://github.com/benedekrozemberczki/awesome-graph-classification?fbclid=IwAR2MZ60VgZGN_juX_8jCe6hwuXLQ5mC2EZTqg8kqAX8AsgTIxznxD8t68QM

線性代數在圖論的應用

一 鄰接矩陣
https://ccjou.wordpress.com/2010/01/18/%E7%B7%9A%E6%80%A7%E4%BB%A3%E6%95%B8%E5%9C%A8%E5%9C%96%E8%AB%96%E7%9A%84%E6%87%89%E7%94%A8-%E4%B8%80%EF%BC%9A%E9%84%B0%E6%8E%A5%E7%9F%A9%E9%99%A3/

二 關聯矩陣
https://ccjou.wordpress.com/2013/08/30/%E7%B7%9A%E6%80%A7%E4%BB%A3%E6%95%B8%E5%9C%A8%E5%9C%96%E8%AB%96%E7%9A%84%E6%87%89%E7%94%A8-%E4%BA%8C%EF%BC%9A%E9%97%9C%E8%81%AF%E7%9F%A9%E9%99%A3/

三 拉普拉斯矩陣
https://ccjou.wordpress.com/2014/12/04/%E7%B7%9A%E6%80%A7%E4%BB%A3%E6%95%B8%E5%9C%A8%E5%9C%96%E8%AB%96%E7%9A%84%E6%87%89%E7%94%A8-%E4%B8%89%EF%BC%9A%E6%8B%89%E6%99%AE%E6%8B%89%E6%96%AF%E7%9F%A9%E9%99%A3/

Demystifying Different Variants of Gradient Descent Optimization Algorithm

https://medium.com/hackernoon/demystifying-different-variants-of-gradient-descent-optimization-algorithm-19ae9ba2e9bc

吳恩達《Machine Learning Yearning》

這是一本相當實務的機器學習手冊，內容講述在執行機器學習專案時常遇到的問題以及如何解決，相當值得一讀！

雖然目前仍無繁中譯本，但已有簡中譯本!

原文：

https://www.deeplearning.ai/machine-learning-yearning/?fbclid=IwAR1DmvMUy4tPj4UjC7r75yF0u4cAsVZKovKZm_YvQI1PIRh9Ffgn4jni74U

簡中譯本：

https://deeplearning-ai.github.io/machine-learning-yearning-cn/docs/home/