Course Abstract
Training duration : 60 minutes
Ever wonder how Facebook’s facial recognition or Snapchat’s filters work?
Faces are a fundamental piece of photography, and building applications around them has never been easier with open-source libraries and pre-trained models. This course provides an introduction to face processing using Computer Vision models. Learners will be exposed to latest techniques used for building applications for face-detection, recognition, manipulation and classification
DIFFICULTY LEVEL: ADVANCED
Learning Objectives
-
You will understand some of the computer vision and machine learning techniques behind applications Snapchat filter and Facebook facial recognition.
-
Develop your own prototypes to tackle tasks such as:
-
Face detection (e.g. digital cameras),
-
Recognition (e.g. Facebook Photos),
-
Classification (e.g. identifying emotions),
-
Manipulation (e.g. Snapchat filters), and more.
Instructor
Instructor Bio:
Founder | Scalar Research
Gabriel Bianconi
Gabriel is the founder of Scalar Research, a full-service artificial intelligence & data science consulting firm. Scalar helps companies tackle complex business challenges with data-driven solutions leveraging cutting-edge machine learning and advanced analytics. Previously, Gabriel was a B.S. & M.S. student in computer science at Stanford, where he conducted research on computer vision, deep learning, and quantum computing. He's also spent time at Google, Facebook, startups, and investment firms.
Background knowledge
-
This course is for current or aspiring Data Scientists, Computer & Machine Learning Engineers, Deep Learning Engineers, AI Product Managers
-
Knowledge of following tools and concepts is useful:
-
Workings of Deep Learning models. Please refer the "Deep Learning with Tensorflow & PyTorch" course by Dr. Jon Krohn in course library.
-
Some familiarity with Computer Vision concepts
-
Good foundation of mathematics for data science