This is repo is my reference for storing my notes, and code when I wanted to take the course CS224d: Deep Learning for Natural Language Processing
The prerequisites of the course is as follows:
- Proficiency in Python All class assignments will be in Python (and use numpy). ]
- College Calculus, Linear Algebra (e.g. MATH 19 or 41, MATH 51) You should be comfortable taking derivatives and understanding matrix vector operations and notation.
- Basic Probability and Statistics (e.g. CS 109 or other stats course) You should know basics of probabilities, gaussian distributions, mean, standard deviation, etc.
- Equivalent knowledge of CS229 (Machine Learning) We will be formulating cost functions, taking derivatives and performing optimization with gradient descent.
So my game plan was to get enough python knowledge and math knowledge to successful learn and finish from this course. Having a through learning of everything is not realistic. This will be a tight stretch, but my plan is as below:
- Go through the codeacademy course on python. Finish it
- Go through learn python in Y minutes. This is will give me enough overview of the syntax I can expect from Python.
- Go through the Linear Algebra course on Khan Academy. Note down all material from notes and videos
- Go through the Statistics and Probability course on Khan Academy. Note down all material from notes and videos
- Go through the introductory Numphy tutorial on the Standford webite
- Install pycharm, python, virtualenv, and IPython on my computer.
- Setup terminal.com for a share-able IPython environment.
- TBD..
Learning Math
- The math part of this course is the troublesome part. I realize I need some sort of strategy to tackle the maths needed for this subject. My first instinct to follow a knowledge tree. I saw a knowledge tree for linear algebra form the book "No Bullshit Guide to Linear Algebra".