Deep Learning for Computer Vision
Completed by Jimut Pal
March 19, 2026
14 hours (approximately)
Jimut Pal's account is verified. Coursera certifies their successful completion of Deep Learning for Computer Vision
What you will learn
Improve model performance and training stability using multilayer perceptrons (MLPs) and applying normalization techniques.
Implement autoencoders for unsupervised feature learning and design Generative Adversarial Networks (GANs) to generate synthetic images.
Train convolutional neural networks (CNNs) for image classification tasks, understanding how layers extract spatial features from visual data.
Apply advanced architectures like ResNet for deep image recognition and U-Net for image segmentation.
Skills you will gain
- Category: Classification Algorithms
- Category: Generative Model Architectures
- Category: Autoencoders
- Category: Dimensionality Reduction
- Category: Convolutional Neural Networks
- Category: Unsupervised Learning
- Category: Model Deployment
- Category: Model Training
- Category: Generative Adversarial Networks (GANs)
