Follow Us On

Deep Learning for Computer Vision Hands-on Workshop

Thu, Sep 19 | Z-Park Silicon Valley

Time & Location

Sep 19, 2019, 4:00 PM – 9:00 PM
Z-Park Silicon Valley, 4500 Great America Pkwy, Santa Clara, CA 95054, USA

About the Event

Instructors: Dr. Kiran Gunnam, Dr. Koji Seto, Dr. Osso Vahabzadeh

 

What you will learn / Topics that will be covered:

  1. Intuitive Treatment
    • Overview of Computer Vision and Deep Learning
    • Convolutional Neural Network (CNN)
    • Deep Reinforcement Learning and Imitation Learning
    • Generative Adversarial Networks (GANs)
    • Introduction to OpenCV
    • Applications: Image Classification, Image Segmentation, Object Detection – Region-based (R-CNN, Fast R-CNN, Faster R-CNN, Mask R-CNN, R-FCN), Single shot (SSD, YOLO), Feature Pyramid Networks (FPN), Image Style Transfer, Image Colorization, Image Reconstruction, Image Super-Resolution, Image Editing, Image Synthesis
  2. In-depth Treatment
    • Real-Time Object Detection: Faster R-CNN, You only look once (YOLO)
    • Image Synthesis with Generative Adversarial Networks (GANs)
  3. Hands-on Practice
    • CNN – Image Classification
    • GANs – Image Synthesis
  4. Project
    • Face Recognition

Target Audiences: Engineers, researchers, practitioners and students who are interested in deep learning and their implementations on GPUs in Computer Vision applications. This workshop will particularly benefit people who intend to build Computer Vision applications using deep learning techniques on top of a solid understanding of underlying algorithms.

Prerequisites: Basic knowledge of Machine Learning, and familiarity with Python and Tensorflow basics

Upon completion of this course, you’ll be able to build Computer Vision applications using deep learning techniques to start solving real-world problems such as Healthcare image analysis and Traffic sign classification.