Intro. How I Plan to Teach Myself Deep Learning Using Only Free Resources
Learning Deep Learning Series Part 1: Videos
Learning Deep Learning Part 2: Online Courses
Learning Deep Learning Part 3: Github Repos
We’re already familiar with the popularity of big data of the past five or so years and we’ve heard that data scientist is the “Sexiest job of the 21st century” countless times, but compared the current hype of deep learning is unlike anything we’ve seen before. It’s the hottest thing in tech and people can’t get enough of it. Each month, there are numerous new startups popping up that are looking to cash in on the neural networks wave. Facebook employees are clamoring each other to sign up for courses at the Facebook Artificial Intelligence Research Lab. We here at Open Data Science have been deeply in involved following the latest trends within deep learning and neural networks
Like most data scientists and people working in data, I’ve followed the rise of deep learning and have decided that I can no longer sit on the sidelines. It’s time to go all in on deep learning!
This is the first article in a series where I will chronicle my experience of teaching myself deep learning with only free resources. I’ll be using a variety of resources including video tutorials, online classes (Udacity, EDX), and Github repos. This series will be a combination of a running diary of my experience and review of the content. I’ll be publishing my thoughts and feelings about the content in addition to grading it as well. For the conclusion of the series I”ll be applying my new deep learning skills on my first deep learning project.
Here’s a brief outline of my learning path:
- Begin my quest for deep learning knowledge with video resources. I don’t want to jump into the coding part yet. The video resources will provide me a base level of understanding before I get into the heavy lifting.
2. Online Courses
3. Github Repos
- For the last section in my learning journey, I’ll be using a curated section of Github repos of Jupyter Notebook. Since I’ve started learning Python two years, I found that annotated Jupyter Notebooks have been helped me go from simply understand a topic or concept to mastering it.
To give you a sense of where I’m starting from, I’ve been a data scientist for about 18 months now. I graduated from the Metis bootcamp in April 2016 and have been writing for ODSC since August 2016. I also work as an Instructional Associate for General Assembly’s part-time data science course. I’m well-versed in machine learning and data analysis, but have only a cursory understanding of deep learning which I’ve attained from attending a couple ODSC workshops and talks.
In the meantime, I’ve uploaded this exhaustive collection of the free resources I plan to use for this series onto this Github repo. I of course will not using and writing about every resource, there are way too much of them for that. If you’re looking to hope onto the deep learning train (without sparing a dime), this is your one-stop shop for deep learning learning.
I'm a journalist turned data scientist/journalist hybrid. Looking for opportunities in data science and/or journalism. Impossibly curious and passionate about learning new things. Before completing the Metis Data Science Bootcamp, I worked as a freelance journalist in San Francisco for Vice, Salon, SF Weekly, San Francisco Magazine, and more. I've referred to myself as a 'Swiss-Army knife' journalist and have written about a variety of topics ranging from tech to music to politics. Before getting into journalism, I graduated from Occidental College with a Bachelor of Arts in Economics. I chose to do the Metis Data Science Bootcamp to pursue my goal of using data science in journalism, which inspired me to focus my final project on being able to better understand the problem of police-related violence in America. Here is the repo with my code and presentation for my final project: https://github.com/GeorgeMcIntire/metis_final_project.
- Why You Should be Using Jupyter Notebooks 149 views | by Daniel Gutierrez, ODSC | under Machine Learning, Modeling
- What Happens to Housing Prices If People Leave a City? 37 views | by Jordan Bean | under Data Visualization, Modeling
- Discovering 135 Nights of Sleep with Data, Anomaly Detection, and Time Series 34 views | by Juan De Dios Santos | under Modeling, Python, R, Statistics, Tools & Languages