Deep Learning: Image Recognition Released: 8/20/2024

Deep Learning: Image Recognition [Released: 8/20/2024]

Deep Learning: Image Recognition
.MP4, AVC, 1280x720, 30 fps | English, AAC, 2 Ch | 2h 14m | 408 MB
Instructor: Isil Berkun

Deep learning and image recognition is everywhere, from unlocking phones to tagging friends in photos. Learning how it works is critical for anyone working in tech today, especially if you want to stay ahead of the curve, sharpen your skills, and prepare to innovate. Join instructor Isil Berkun as she shows you how to make computers recognize images, how to prepare pictures for AI, and how to build systems that can tell who's who. Along the way, learn about what to avoid and what to do when common problems arise. By the end of this course, you'll be prepared to build image recognition models and start exploring how to make AI more creative with images.

This course is integrated with GitHub Codespaces, an instant cloud developer environment that offers all the functionality of your favorite IDE without the need for any local machine setup. With GitHub Codespaces, you can get hands-on practice from any machine, at any time-all while using a tool that you'll likely encounter in the workplace. Check out the "Using GitHub Codespaces with this course" video to learn how to get started.

Learning objectives

Apply the fundamentals of image processing for model training and achieving better performance in image recognition tasks.
Understand the mechanics of CNNs and explore advanced CNN architectures like ResNet and Inception to apply to projects.
Implement a simple image detection model using a pretrained CNN and apply it to different images to understand image classification.
Implement techniques for cleaning, transforming, and feeding data into models for optimal deep learning performance.
Build on the basics of image detection to create systems that can recognize and distinguish individual images.
Select and apply the right metrics to assess model performance and refine models.
Understand the challenges and limitations of current image recognition technologies and ethical implications.