Deep Learning from Scratch Using Python


Details
Abstract:
Many of us have used libraries like Keras and TensorFlow to train Deep Learning models. But very few of us fully understand what is going on "under the hood."
In this talk, we'll walk through how to create Deep Neural Networks powerful enough to solve image classification tasks, from scratch, using Python. We'll do everything from coding the layers of our network using classes, to implementing the backpropogation algorithm so the layers work correctly together, and implementing a number of different neural net training optimization techniques such as Dropout, Momentum, and Weight Regularization.
We'll end up with a Jupyter notebook running a flexible deep learning framework live that can then be extended to create arbitrarily deep networks - all from scratch!
Bios:
Seth Weidman
Seth joined Metis from Trunk Club, where he built their lead scoring models and contributed to their recommender systems. He transitioned into Data Science from management consulting by taking courses on Coursera and Udacity; this experience made him passionate about alternative education experiences such as MOOCs and bootcamps, which led him first to teach data science part time for General Assembly and ultimately led him to join Metis. Seth has Mathematics and Economics degrees from The University of Chicago.
Sponsors and Acknowledgments:
Special thanks to Nataljia Ulemek from Rakuten
http://rakuten.careers (http://rakuten.careers/) for hosting this meetup
and to INTEL for providing Pizza and drinks!
Intel also created a mini contest for all the participants. If you have a ML project and want to showcase it, share it, or collaborate it with others, submit it to DevMesh. Everyone who submits a project to DevMesh will get remote access to Machine Learning Servers. On top of that, any submitted project will receive a $50 gift card
Instructions to join DevMesh:
1/ Create a new account at devmesh.intel.com (http://devmesh.intel.com/)
2/ Join your dedicated group - Artificial Intelligence East Coast (https://devmesh.intel.com/groups/448)
3/ To submit a project, click on “add a project”
*when submitting your project, make sure to select “Artificial Intelligence East Coast (https://devmesh.intel.com/groups/448)” as your group.
To receive invitations for Intel webinars, news and tools for Machine Learning and Deep Learning, register on this link (https://plan.seek.intel.com/us_en_software_registration-form_DeveloperMeetupFollow-up_html?registration_source=florida_meetup).
Directions to Rakuten:
https://secure.meetupstatic.com/photos/event/d/9/f/4/600_464875796.jpeg
https://secure.meetupstatic.com/photos/event/d/a/0/4/600_464875812.jpeg

Deep Learning from Scratch Using Python