Introduction to Deep Learning

Hi Everyone,

Welcome to Norfolk Data Science Meetup.

Meetup Topic: Introduction to Deep Learning

Presenter: Xiaodong Yu

What is this talk about?

Deep learning is a hot buzz word nowadays. In this one-hour talk, we will try to cover the following topics and hopefully give beginners an overview and good starting point of deep learning:

1) What is deep learning?
2) What is the relationship between deep learning and traditional machine learning algorithms, especially neural networks?
3) Why did it “suddenly” become so popular in recent years?
4) What are the secret weapons that make it so successfully in some domain?
5) What types of problems are particularly suitable for DL and what are not?
6) What is the limitation of DL?
7) What tools or frameworks of DL are ready to use?
8) If I am interested in DL, where I can find good tutorials and how I can study it by myself?

Complete beginners are welcome.

Please comment below if you have any questions and I hope to see you there.

Cheers!

About Presenter:

Xiaodong is an AI researcher and entrepreneur from Virginia Beach and previously worked as a Senior Researcher at Comcast. He is a Ph.D. scholar from the University of Maryland College Park and holds several patents in the area. More: https://www.linkedin.com/in/yuxiaodong/

Relevant online resources:

The courses are usually very friendly to beginners
https://www.coursera.org/specializations/deep-learning
or search “deep learning” in coursera.com, udacity.com, edx.org, etc.

More serious learners can go to Stanford University website (https://cs230.stanford.edu/) to check out the lecture videos and notes for Deep Learning course for their undergraduates. Researchers can see the most recent development in this field in international conferences such as CVPR, ICML, NeurIPS, etc.

Prior Installations/Setup (Optional):

Jupyter Notebook: http://joshlawman.com/getting-set-up-in-jupyter-notebooks-using-anaconda-to-install-the-jupyter-pandas-sklearn-etc/

GitHub Repo: Links will be updated soon in the comments.