Deep Learning for Computer Vision Specialization

 What you'll learn

Apply the full deep learning workflow to real-world projects like detecting parking signs

Retrain common classification and detection models like ResNet and YOLO

Train and calibrate specialized models known as anomaly detectors

Generate synthetic training images and use AI-assisted auto-labeling to save time and money

Join Free: Deep Learning for Computer Vision Specialization

Specialization - 3 course series

This hands-on specialization dives in quickly, so you can start training models and gain practical deep learning skills. You don’t need to be an expert programmer or have prior deep learning experience to quickly gain valuable career skills for this rapidly growing area.

Deep learning empowers engineers and scientists to tackle complex problems in computer vision that were previously challenging to solve, such as building autonomous systems like self-driving cars. As companies increasingly adopt computer vision technologies, professionals with deep learning skills are in high demand. Acquiring these skills will give you a competitive advantage in a rapidly changing technological landscape.

By the end of this specialization, you will be able to:

Train image classification and object detection models

Train specialized models to detect anomalies

Evaluate model performance using more than just prediction accuracy 

Interpret model behavior by investigating prediction errors

Improve model performance by tuning important parameters

Use AI-assisted labeling to automatically label thousands of images

Generate synthetic images to for training using data-augmentation

For the duration of the specialization, you will have free access to MATLAB, software used by top employers worldwide. The courses draw on the applications using MATLAB, so you spend less time coding and more time applying deep learning concepts.

Applied Learning Project

As part of the specialization, you will apply your skills to solve real-world problems through hands-on projects. You’ll train a classifier that identifies the letters of American Sign Language. Then, you will train an object detection model to find and identify parking signs as needed for autonomous driving. Lastly, you’ll detect anomalies in medical images and perform AI-assisted data annotation to label new data for training.