Online Course – Google’s Certified Professional Internship in Deep Learning for Computer Vision

Advance your engineering career with AI skills. Learn practical deep learning techniques for computer vision.

Suggested by: Coursera (What is Coursera?)

Professional Certificate

Beginners

No prior knowledge required

Time to complete the course

7-day free trial

No unnecessary risks

Skills you will acquire in the course

  • Train models for image classification and object recognition
  • Train special models for anomaly detection
  • Evaluate model performance by going beyond meeting expectations of forecast accuracy
  • Interpret the model’s behavior by studying the forecast errors
  • Improve model performance by tuning important parameters
  • Use AI inference to automatically classify thousands of images
  • Create synthetic images for training using data augmentation

What you will learn in the course

Courses for which the course is suitable

  • Machine Learning Engineer
  • Data Scientist
  • Software Engineer in the field of AI
  • Computer vision systems developer
  • Autonomous Systems Engineer
  • Medical Data Analyst
  • Object recognition model developer
  • Anomaly detection solutions developer
  • Software developer with expertise in MATLAB
  • Image classification system developer

Internship – Series of 3 courses

This specialization is a fast-paced entry into the field, so you can start training models and developing practical deep learning skills. You don’t need to be an expert programmer or have prior deep learning experience to gain valuable professional skills in this rapidly expanding field.

Deep learning enables engineers and scientists to tackle complex computer vision problems that were previously difficult to solve, such as building autonomous systems like driverless cars. As companies increasingly adopt computer vision technologies, there is a high demand for professionals with deep learning skills. Acquiring these skills will give you a competitive edge in the rapidly changing world of technology.

At the end of this internship, you will be able to:

  • Train models for image classification and object recognition
  • Train special models for anomaly detection
  • Evaluate model performance by going beyond meeting expectations of forecast accuracy
  • Interpret the model’s behavior by studying the forecast errors
  • Improve model performance by tuning important parameters
  • Use AI inference to automatically classify thousands of images
  • Create synthetic images for training using data augmentation

While you’re in the internship, you’ll have free access to MATLAB, a software used by leading companies around the world. Courses focus on applications using MATLAB, so you’ll spend less time coding and more time applying deep learning concepts.

Hands-on Learning Project

As part of the internship, you will apply your skills to solve real-world problems through hands-on projects. You will train a classifier that recognizes the letters of American Sign Language. Then, you will train an object recognition model to find and identify parking signs as needed for autonomous driving. Finally, you will identify anomalies in medical images and annotate data using AI to label new data for training.

Details of the courses that make up the specialization

Introduction to Deep Learning for Computer Vision

Course 1 • 9 hours

What will you tell?

  • Developing a strong foundation in deep learning for image analysis
  • Retraining well-known models like GoogLeNet and ResNet for specific applications
  • Studying model behavior to identify errors, determine potential solutions, and improve model performance
  • Using a real project to practice the full deep learning process

Skills you will gain

  • Artificial Intelligence (AI)
  • Computer vision
  • Deep learning
  • Matlab
  • Image classification