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

University of Michigan

Deep Learning for Computer Vision

University of Michigan via YouTube


Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification and object detection. Recent developments in neural network approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into details of neural-network based deep learning methods for computer vision. During this course, students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. We will cover learning algorithms, neural network architectures, and practical engineering tricks for training and fine-tuning networks for visual recognition tasks.


Lecture 1: Introduction to Deep Learning for Computer Vision.
Lecture 2: Image Classification.
Lecture 3: Linear Classifiers.
Lecture 4: Optimization.
Lecture 5: Neural Networks.
Lecture 6: Backpropagation.
Lecture 7: Convolutional Networks.
Lecture 8: CNN Architectures.
Lecture 9: Hardware and Software.
Lecture 10: Training Neural Networks I.
Lecture 11: Training Neural Networks II.
Lecture 12: Recurrent Networks.
Lecture 13: Attention.
Lecture 14: Visualizing and Understanding.
Lecture 15: Object Detection.
Lecture 16: Detection and Segmentation.
Lecture 17: 3D Vision.
Lecture 18: Videos.
Lecture 19: Generative Models I.
Lecture 20: Generative Models II.
Lecture 21: Reinforcement Learning.
Lecture 22: Conclusion.

Taught by

Michigan Online


5.0 rating, based on 2 Class Central reviews

Start your review of Deep Learning for Computer Vision

  • I must commend the efforts pull up for this course and my beat regards to all the lecturer involved in this course
  • Profile image for Ilya Rudyak
    Ilya Rudyak
    If you’re interested in Deep Learning chances are you’re familiar with brilliant cs231n CNN for Computer Vision. Personally I started with the 1st offering in 2015 which was taught by Andrej Karpathy (as you may see that was the only time when he taught...

Never Stop Learning.

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