LearningFromTheBest

This project is to list the best books, courses, tutorial, methods on learning certain knowledge, for free

Machine Learning Courses and Books:

Introduction Course: Coursera's "Machine Learning" by Andrew Ng.

-- 2008 youtube version is not introducionary

-- Do NOT spend time on Octave/Matlab unless you already knew it

Introduction Course2(I think this is the best one): Andrew Ng's deeplearing.ai course: https://www.youtube.com/channel/UCcIXc5mJsHVYTZR1maL5l9w/playlists

Introduction Course 3: Caltech "Learning from Data" by Yasar

Introduction Course 4: Fast.ai "Practical Deep Learning for Coders" by Jeremy Howard. It uses PyTorch

Tutorials on different topics: http://bit.ly/36skFE7

Advanced Courses: Stanford cs231n(CNN) and cs224n(NLP)

Book on DeepLearning: www.deeplearningbook.com (by now, it's the only one and it's free)

Book on Reinforcement Learning: Reinforcement Learning: An Introduction

Course on Reinforcement Learning: David Silver's course

Course on Advanced Reinforcement Learning: UCB CS294 fall 2017/2018, UCB CS285 2019

How to read ML papers: https://deeps.site/blog/2019/10/14/reading-research-papers-career-advice/

Deep Bayesian Network: https://github.com/bayesgroup/deepbayes-2019

Data Driver Algorithm Design: https://sites.google.com/view/cs-159-spring-2020/

Machine Learning Papers, blogs, conferences:

Paper trend: http://www.arxiv-sanity.com/

Paper with cite/references/categorize: https://www.semanticscholar.org/paper/

Paper with review: https://openreview.net/

Paper Explained: https://towardsdatascience.com/

w

Paper with Code: https://paperswithcode.com/

Berkeley: https://bair.berkeley.edu/blog/

OpenAI: https://spinningup.openai.com/en/latest/index.html

DeepMind Research/Blog: https://deepmind.com/research

CrossMind: https://crossminds.ai/

ICML(RL): https://slideslive.com/38930488/modelbased-methods-in-reinforcement-learning-part-1-introduction-learning-models

Personal Blogs

RL blog(Onwer is working on bitcoin and stopped updating): http://www.wildml.com/

Lex podcast: https://lexfridman.com/ai/

LiLian's RL blog: https://lilianweng.github.io/lil-log/

Import AI(recommended by quite some) https://jack-clark.net/

Best papers collection: https://jeffhuang.com/best_paper_awards.html

Colah's blog(famous for LSTM): https://colah.github.io/

Someone's paper collection (I'm doing similar): https://github.com/number9473/nn-algorithm/issues

Pinterest Practical MultiTask AutoML: https://medium.com/pinterest-engineering/how-we-use-automl-multi-task-learning-and-multi-tower-models-for-pinterest-ads-db966c3dc99e

RL Framework

openAI gym (most widely used)

openAI procGen: https://openai.com/blog/procgen-benchmark/

facebook ELF

deepmind pysc2

deepmind opensiel(C++ and Python, both env and algo): https://github.com/deepmind/open_spiel

Card: https://github.com/datamllab/rlcard

Portfolio Management(based on Gym): https://github.com/MRYingLEE/Portfolio_GYM

Portfolio Management(no git repo): https://www.slideshare.net/KamerAliYuksel/deep-reinforcement-learning-portfolio-management

Benchmark site: https://app.wandb.ai/cleanrl/cleanRL?workspace=user-

ML Tools, Playground, and Framework

Googl OR tools: https://developers.google.com/optimization

Google Colab: https://colab.research.google.com/notebooks/welcome.ipynb

Github repo for ML

OpenAI Baseline(TF1.x):

Stable Baseline(better Baseline, with dis/cont comments): https://github.com/hill-a/stable-baselines

TensorLayer RLZoo(TF2.0): https://github.com/tensorlayer/RLzoo

ML in IC: https://github.com/kouroshHakha/bag_deep_ckt

PathFinding: https://github.com/cair/deep-maze

Alpha-Star: https://github.com/imagry/aleph_star

VIN: https://github.com/kentsommer/pytorch-value-iteration-networks

GNN: https://github.com/thunlp/GNNPapers

GNN(NTU): https://graphdeeplearning.github.io/

NLP progress: https://github.com/sebastianruder/NLP-progress

PyTorch RL: http://github.com/shangtongzhang/DeepRL

PyTorch Baseline(with c++ implementation too): https://github.com/navneet-nmk/pytorch-rl

Alpha-Zero: https://github.com/suragnair/alpha-zero-general

Replay Buffers: https://ymd_h.gitlab.io/cpprb/examples/

MultiAgent: https://github.com/ChenglongChen/pytorch-MADRL

DGL(from aws): https://github.com/dmlc/dgl

Karpathy(minGpt is interesting): https://github.com/karpathy

ML Contest

House Price Predicting(hybrid input): https://www.kaggle.com/serigne/stacked-regressions-top-4-on-leaderboard

Power Grid Management: https://l2rpn.chalearn.org/power-grid-in-action

Kaggle 2-Sigma Financial Modeling: https://www.kaggle.com/c/two-sigma-financial-modeling

Kaggle 2-Sigma Financial News: https://www.kaggle.com/c/two-sigma-financial-news

Path Finding

Combining Q-Learning and Search with Amortized Value Estimates https://arxiv.org/abs/1912.02807

Reinforcement Learning with A* and a Deep Heuristic https://arxiv.org/abs/1811.07745

Progressive tracking

Object Detection: https://github.com/yehengchen/Object-Detection-and-Tracking

RL: http://louiskirsch.com/maps/reinforcement-learning

GNN: https://github.com/thunlp/GNNPapers#natural-language-processing

PyTorch Explained: https://arxiv.org/abs/1912.01703v1

Hardware-Software Co-Optimization: https://tvm.apache.org/

General Algorithm:

Course: MIT "Introduction to Algorithms"

Book: MIT "Introduction to Algorithms"

Site: Leetcode.com

Algorithm with Python: http://interactivepython.org/runestone/static/pythonds/Introduction/toctree.html

Linear Algebra:

Course: MIT "Linear Algebra" by Strang

Introduction Book: "Linear Algebra Done Right"

Book on Nemeric: Matrix

Statistics:

Course: MIT https://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041sc-probabilistic-systems-analysis-and-applied-probability-fall-2013/

Packages: pymc3 https://docs.pymc.io/

Python:

Introduction Book: Learning Python

Advanced Book: Python document

Advanced Tutorial: Stackoverflow

Packages: NumPy, SciPy, Pandas

Python GUI package:

Eel:A little Python library for making simple Electron-like HTML/JS GUI apps.(See Electron) https://github.com/samuelhwilliams/Eel

pywebview: Build GUI for your Python program with JavaScript, HTML, and CSS (wrapper around webview, display it in gui)

flaskwebgui: Create desktop applications with Flask (light weight and simple webview wrapper) https://github.com/ClimenteA/flaskwebgui

PySimpleGUI: Create custom layout GUI's simply(convert tkinter, Qt, Remi, WxPython): https://github.com/PySimpleGUI/PySimpleGUI

Tips on profit: https://cryptolens.io/2019/11/tips-on-monetizing-python-applications/

CPP:

C++ FAQ: http://yosefk.com/c++fqa/templates.html

JavaScript:

Advanced Book: Oreilly "Javascript the Good Parts" by Douglas Crockford

DataVisualization(D3):

Introduction Book: Oreilly "Interactive Data Visualization for the web" by Scott Murphy

Web Package: D3

Python Package: vispy, bokeh, dash(plotly)

Frameworks: grafana, superset

Quant and ML:

Introduction Book: "Algorithmic Trading" by Ernie Chan

Course: Coursera "Quantization Financial" (only one really covers this topic?)

Paper Site: qwafafew.org

Resource Site: https://www.quantopian.com/tutorials

Another Quant Site: https://quantocracy.com/

Packages: zipline, pyalgotrade, vnpy, easytrade

2-sigma: https://www.twosigma.com/insights/article/25-of-our-favorite-papers-talks-presentations-and-workshops-from-nips-2017/

Financial Sentiment Analysis: github.com/ProsusAI/finBERT

Sentiment Analysis in Action: http://www.alternative-analytics.eu/dashboard/sentiment.html

Advances in Financial Machine Learning: https://github.com/hudson-and-thames/research

NewsCatcher(w/o NLP process): https://github.com/kotartemiy/newscatcher

Cointegration: https://github.com/daehkim/pair-trading/blob/master/pairSelection.ipynb

Pair Trading 1: https://israeldi.github.io/coursework/EECS545/545_Final_Project.pdf

Quant and ML -- Papers

Universal features of price formation in financial markets: perspectives from Deep Learning https://arxiv.org/abs/1803.06917

DataBase:

Introduction Book:

Course:

TimeSeries DataBase: InfluxDB (becuase of IoT)

DB: mysql/mariadb (easy available); postgresql (solid)

---- Not Necessary Best Resource ----

Bioinformatics:

Deep Learning Usage Summary: "Deep learning in bioinformatics"(https://academic.oup.com/bib/article/18/5/851/2562808)

Alternative Deep Learning usage Analysis: "Opportunities and obstacles for deep learning in biology and medicine" (http://rsif.royalsocietypublishing.org/content/15/141/20170387#sec-15)

Online Course: "Deep Learning in Genomics and Biomedicine" (https://canvas.stanford.edu/courses/51037)

Bio Paper Site: bioarxiv.org

Gene Sequencing Read:

Nanopore tech: "The evolution of nanopore sequencing" (https://www.frontiersin.org/articles/10.3389/fgene.2014.00449/full)

Tool Comparison: "Comprehensive comparison of Pacific Biosciences and Oxford Nanopore Technologies and their applications to transcriptome analysis" (https://f1000research.com/articles/6-100/v1)

NanoPore practice: DeepNano: Deep Recurrent Neural Networks for Base Calling in MinION Nanopore Reads http://compbio.fmph.uniba.sk/deepnano/

Machine Learning in Gene: https://www.biorxiv.org/content/biorxiv/early/2015/11/16/031906.full.pdf

RNN in sequencing: An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling https://arxiv.org/pdf/1803.01271.pdf

Cancer Imaging:

Cone Beam Imaging: "https://sinews.siam.org/Details-Page/achieving-real-time-cone-beam-ct-reconstruction-1"

Image Reconstruct: "A Deep Learning Architecture for Limited-Angle Computed Tomography Reconstruction" (https://pdfs.semanticscholar.org/ae41/8b253c235138ef1671fa1053be2f17ef2aa8.pdf)

Throax Disease Classification: https://arxiv.org/pdf/1801.09927.pdf

Education:

How to Get Into Harvard and the Ivy League: https://blog.prepscholar.com/how-to-get-into-harvard-and-the-ivy-league-by-a-harvard-alum#part2