Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Wolfram U

Convolutional Neural Networks for Computer Vision Video Course: Wolfram U

via Wolfram U

Overview

Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
Learn to use CNNs for image processing and computation. Course covers practical applications in image classification, segmentation, reconstruction and generative modeling. How to design and train your own neural nets.

Convolutional neural networks (CNNs) have revolutionized the way we process and understand image data. In this course, you'll explore the role of CNNs in image computation, beginning with the properties of visual data and how the human visual system influences image processing techniques. The course covers the key building blocks of neural networks, discussing network layers, methods to enhance training and techniques to analyze networks through receptive fields, sensitivity maps and feature visualizations. The course also highlights innovative architectures like Inception, ResNets and U-Nets, as well as emerging designs such as visual transformers. Finally, we examine practical applications in image classification, segmentation, reconstruction and generative modeling, showcasing the wide range of possibilities CNNs offer for advancing image computation. Wolfram AI Course Assistant is available for this interactive course.

Syllabus

  • Use convolutional neural networks for image processing and computation
  • Understand basic structures of neural networks and how to design and train your own neural nets
  • Apply neural networks to image processing and computation
  • Use some advanced types of neural net structures

Reviews

Start your review of Convolutional Neural Networks for Computer Vision Video Course: Wolfram U

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.