My Process for Learning Natural Language Processing with Deep Learning
I currently work as a Data Scientist for Informatica and I thought I’d share my process for learning new things. Recently I’ve been wanting to explore more into Deep Learning, especially Machine Vision and Natural Language Processing. I’ve been procrastinating a lot, mostly because it’s been summer, but now that it’s fall and starting to cool down and get dark early, I’m going to be spending more time learning when it’s dark out. And the thing that deeply interests me is Deep Learning and Artificial Intelligence, partly out of intellectual curiosity and partly out of greed, as most businesses and products will incorporate Deep Learning/ML in some way.
I started doing research and realized that an understanding and knowledge of Deep Learning was within my reach, but I also realized that I still have a lot to learn, more than I initially thought. So I did what any person does when they want to learn, I went to the library…I’m just kidding this isn’t 1995. I found a graduate level standord course that had class materials available for free online. http://cs224d.stanford.edu/.
I went straight to the syllabus and checked the prerequisites. Then I started going through the course material. I decided I needed to take the prerequisite courses in order to understand the material best. I needed Linear Algebra, and Machine Learning knowledge and a knowledge of Convolutional Neural Networks. So here’s the curriculum I put together that will work for anyone with a serious interest in deep learning.
Im gonna be going through this during my nights. I’m hoping to have a solid understanding of the concepts by January. That will provide me with a base to work on other projects that I have dreamt up that require Natural Language Processing.
Also a note on my learning style, I prefer to learn in a self paced manner, so when given the choice I will choose the Stanford courses over Coursera as the latter are released in weekly sections and Stanford courses are available all at once.