逝川

Fundamental Knowledge for Deep Learning & Natural Language Processing

This list just includes the core of related knowledge in deep learning and natural language processing. The all the courses listed here is personally tested by myself. I believ they are the best until now from and only from my personal persepctive. This list is updating as time goes on...

Natural Language Processing *

• Book
  • Dan Jurafsky( 3rd)
  • Manning
  • Natural Language Processing-Jacob Eisenstein-Nov 13, 2018

• Course

  • CS 124: From Languages to Information (First course in NLP!)
  • CSE490U: Natural Language Processing - Winter 2017 (for undergraduates) - Noah Smith

  • CSEP 517: Natural Language Processing - Spring 2017 (for professional master students) - Noah Smith

    • University of WashingtonInstructor: Noah Smith
    • Syllabus and Vedio Lectures
  • CSE 517: NLP (for Ph.D. students)-Spring 2018 - Noah Smith
  • CSE 599D1: Advanced NLP (for Ph.D. students)-Spring 2016 - Noah Smith
  • 601.465 - Natural Language Processing - Fall 2017 - Jason Eisner
  • COMP 790.139: Natural Language Processing (Fall 2017)- Mohit Bansal
  • CS4650 - Natural Language Understanding (Spring 2017) - Jacob Einsten
  • CMU NLP Courses (Theory+Practice)
    • CMU CS-11-711: Algorithms for NLP, Fall 2017
    • CMU CS 11-747: Neural Networks for NLP, Spring 2019
  • CIS 700: Advanced Machine Learning for Natural Language Processing-Dan Roth
  • Fall 2016 – CS6501 Natural Language Processing – Kw Chang
  • CS269 Seminar: Machine Learning in Natural Language Processing - Kw Chang
  • CMU-CS-11-731: Machine Learning and Sequence to Sequence Models -Graham Neubig

---

Machine Learning

Introduction Level

• Book
  • A Course in Machine Learning(2017 2ed.超级经典！) - by DumIII
  • ​

• General Notations and Introduction
  • Neural Networks Demystified (非常好的神经网络入门讲解资源- from youtube)

• Course
  • COMS W4995 - Applied Machine Learning - Spring2019 - Andreas C. Müller（偏重实践，极佳入门）
  • CMU-10601- Introduction to machine learning
    • Spring 2015(with all meterials)
    • Spring 2018(only slides)
  • CS229- Fall 2017 - Andrew Ng. *
  • Machine Learning - Fall 2017 - 李宏毅 *
  • DS-GA 1003 Spring 2017- Machine Learning and Computational Statistics
  • OXFORD - Machine Learning( 2014~2015) - Nando de Freitas
  • CPSC340 - Machine Learning and Data Mining - (Undergraduate Level)-2012 - Nando de Freitas
  • CPSC540 - Machine Learning - Mastter Level -2013-Nando de Freitas
  • CS446 - Machine Learning - Dan Roth

More Advanced

• Alex Smola (very important and systematic)-Ph.D. Level*

  • CMU-10701-Fall 2015: Introduction to Machine Learning
  • CMU-10715-Fall 2015: Advanced Introduction to Machine Learning

• Spring 2017 – CS6501 Advanced Machine Learning – Kw Chang

• OXFORD 2016-2017–Advanced Machine Learning

• CMU-10-725-Fall 2016: Convex Optimization

• CMU-10-702-Spring 2017: Statistical Machine Learning

  Assuming sutdent have taken: 10-715 and 36-705

• NYU-DS-GA-1005 - Inference and Representation

---

Deep Learning

• Book
  • Deep Learning Book - Ian Goodfellow etc.
  • -Dive into Deep Learning- Li Mu and Alex Smola（非常重要）
    • 中文版
    • 英文版
• General and Introduction
  • 深层神经网络涉及理念（vedio）
  • Deep Learning 公开课-Yann LeCun

General Deep Learning

• Course
  • UC Berkely(适合入门，hands on！)
    • Berkeley STAT-157: Introduction to Deep Learning (Mxnet based，十分重要可作为第一门课程)
    • 上述课程李沐早期版本（中文）
  • Stanford CS 230- Deep Learning(Andrew Ng)
  • Neural Networks for Machine Learning (Hinton)
  • Machine Learning and Having It Deep and Structured - Spring 2018-李宏毅(持续更新中)
  • MLDS - Spring 2017 - 李宏毅
  • EPFL-IDIAP-EE-559-Deep Learning
  • MIT 6.S191: Introduction to Deep Learning
  • CMU-Deep Learning
    • CMU-11-785: Introduction to Deep Learning
    • CMU-10-707: Deep Learning
  • DS-GA-1008 Deep Learning, Spring 2017- Yann LeCun
  • fast.ai
    • course

For Natural language processing *

• CMU-CS 11-747- Neural Networks for NLP-Spring 2019
• OXFORD- Deep Learning for Natural Language Processing: 2016-2017 (Phil Blunsom)
  • Home page
  • Github-lecture resources
• Stanford-CS224N: Natural Language Processing with Deep Learning-2018
  • Home page, 2017 page
  • Video lecture
• (Small Lesson) - Embeddings and Deep Learning - Hinrich Schutze
• DS-GA 1011 Fall 2017- Natural Language processing with Representation Learning ( Bowan and Cho )
  • Lab Git Repository

For Computer Vision

• Course
  • Stanford CS 231N
  • Learning to see (很好的讲CV入门的课程，from youtube)

---

Reforcement Learning ( with deep or not)

• Introduction and General notations
  • Introduction to RL- by [Joelle Pineau]

• Course
  • CS294-UC Berkeley-Deep Reinforcement Learning, Spring 2017
  • CS234 - Stanford
  • CMU-10370- Deep Reinforcement Learning and Control Spring 2017
  • David Sliver’s Reinforcement Learning Course-2015
  • Introduction to Reinforcement Learning- Udacity

---

Mathematics

Calculus

• Single Variable Calculus (MIT 18.01)
• Auroux - Maltivariable Calculus -2017-Fall
  • Lectures(mit 18.02)

Linear / Abstract Algebra

• Book
  • Introduction to linear algebra 5-th edition
  • Coding the Matrix: Linear Algebra through Applications to Computer Science. 1st
    • It’s corresponding course: The Matrix in Computer Science.
• Course
  • MIT 18.06- Strang (Should be the FIRST CHOICE!) *
    • 18.06 on OCW with vedio lectures
    • 18.06-SC
    • (Optional) MIT 18.06 -Fall 2017-new by other people.
  • Essence of Linear algebra(3Blue1Brown)
  • Coding the Matrix

---

Probabaility, Stats and Informaton theory

• BOOK

  • Probability and Statistics 4th - DeGroot & Schervish

• Course

  1. MITx-6.041Probability
  • HARVARD - Statistics 110: Probability (Should be the first one!) *
  • CS109: Probability for Computer Scientists (Or this is the 1st) *
  • DS-GA 1001 Introduction to Data Science (2017)
    • Jupyter Versions
  • DS-GA 1002: Statistical and Mathematical methods(2015)
  • DS-GA 1002: Probability and Statistics for Data Science(2017)
  • DUKE-STA663: Computational Statistics and Statistical Computing ( Should be the first one! )
  • CMU-10-705: Intermediate Statistics - Larry Wasserman
  • ECE598: Information-theoretic methods in high-dimensional statistics
  • STAT364/664: Information theory

Math for Machine Learning

• Book
• Video

Math for CS and EE

1. EE103/CME103: Introduction to Matrix Methods

2. Computational Science and Engineering- Gilbert Strang

   • I: MIT18.085

   • II: MIT18.086

• Stanford-CS103 - Mathematical Foundations of Computing
• Mathematics for Computer Science

---

Hands-ON AND APPLICAITON ORIENTED

Tensorflow

• Stanford CS20- Tensorflow for deep learninng research
• TensorFlow_Course
• Tensorflow for deep learning research(youtube)
• Deep Learning with Tensorflow(EdX)
• TensorFlow 101

Pytorch

• x
• y

MxNet

• ​
• ​

DyNet

• Homepage

---

Data Science

First of all, a curriculum about data science created by David Venturi is here. It’s serious and important for someone want to engage into data science. I promise!

• Book
  • Python Data Science HandBook

• Course
  • Duke-BIOS 821: Data Science Foundations with Python