Please register on Eventbrite: http://bit.ly/Keras-openCV-for-Computer-Vision and RSVP is closed on this meetup page.

This full day workshop will be led by computer vision expert Andrew Ferlitsch from the Google AI team and ML GDE Margaret Maynard-Reid.

Schedule:
-------------
9:30AM Check-in and breakfast
10:00AM Event start
12:00PM Lunch break
3:00PM Event end

Parking:
-----------
Only street parking is available. Here are some options nearby: the nearby U-Park lots are Lot 52, Lot 58, Lot 62, Lot 71, Lot 72, Fremont #81, and the Red Door Lower Garage #71B.

Audience:
-------------
Software Developers seeking to transition to a Machine Learning Engineering (MLE), or anyone who is interested in learning about computer vision with Keras and OpenCV.

Prerequisite:
-----------------
Python programming, comfortable with numpy and has previously coded a basic convolutional neural networks, such as in an online course.

Abstract:
------------
As AI/ML become more accessible to non-researchers, tech companies are now looking for experienced engineers or data scientists who can apply machine learning principles to production grade software. They can understand the core principles, best practices, design patterns, and expertise with a ML framework/toolset.

Take-Away:
--------------
For the attendees that have previously taken a ML course or self-taught, but don’t feel they are ready for a production environment, this course purpose is to push your over that final hurdle.

Content
-----------
Session 1: Computer Vision Models
Overview of CNN
Sequential CNN
Residual Network CNN
Wide Layer CNN
Densely Connected CNN
Stem Groups
Representational Equivalence

Session 2: Computer Vision Data Engineering
Data Curation
Data Collection
Data Preprocessing (openCV and Keras)
Data Augmentation (openCV and Keras)

Session 3: Computer Vision Training and Deployment
Hyperparameters
Training
Deployment
Hyperparameter Search
Prebuilt Models and Transfer Learning

Session 4: Computer Vision models On-device
We will wrap up the event with on-device ML and how to deploy your trained computer vision models to mobile and IoT.