Learning Outcomes

In this free course, you will learn how to:

• Outline the concept of attention models in computer vision
• Recognize the significance of attention mechanisms in image captioning
• Discuss the effect of transformers in enhancing the speed of training models
• Discuss the notion of various generative models in deep learning
• Explain the significance of variational autoencoders in deep generative models
• Identify the procedure for improving the image quality by mapping VAEs and GANs
• Explain the process of generating images across multiple domains
• Describe the association of disentanglement with variational autoencoders
• Discuss the process of editing images and videos using deep generative models
• Explain the significance of self-supervised learning in computer vision
• State the procedures for tackling the malfunctions of learning models
• Summarize the functions of neural architecture search in deep learning