This report summarizes the tutorial on *Generative Adversarial Networks (GANs)* presented by Ian Goodfellow at NIPS 2016. The tutorial covers several key aspects of GANs, including: 1. **Why Generative Modeling is Important**: It discusses the value of generative models in various applications, such as training and sampling from high-dimensional probability distributions, reinforcement learning, semi-supervised learning, and multi-modal outputs. 2. **How Generative Models Work**: The tutorial explains how generative models work in general and how GANs compare to other generative models. 3. **Details of GANs**: It delves into the specifics of how GANs work, including the game-theoretic framework, the training process, and cost functions. 4. **Research Frontiers in GANs**: The tutorial highlights current research directions and challenges in GANs. 5. **State-of-the-Art Image Models**: It covers state-of-the-art image models that combine GANs with other methods. The tutorial also includes three exercises for readers to complete and provides solutions to these exercises. The slides for the tutorial are available in PDF and Keynote formats, and a video recording of the presentation is expected to be made available later.This report summarizes the tutorial on *Generative Adversarial Networks (GANs)* presented by Ian Goodfellow at NIPS 2016. The tutorial covers several key aspects of GANs, including: 1. **Why Generative Modeling is Important**: It discusses the value of generative models in various applications, such as training and sampling from high-dimensional probability distributions, reinforcement learning, semi-supervised learning, and multi-modal outputs. 2. **How Generative Models Work**: The tutorial explains how generative models work in general and how GANs compare to other generative models. 3. **Details of GANs**: It delves into the specifics of how GANs work, including the game-theoretic framework, the training process, and cost functions. 4. **Research Frontiers in GANs**: The tutorial highlights current research directions and challenges in GANs. 5. **State-of-the-Art Image Models**: It covers state-of-the-art image models that combine GANs with other methods. The tutorial also includes three exercises for readers to complete and provides solutions to these exercises. The slides for the tutorial are available in PDF and Keynote formats, and a video recording of the presentation is expected to be made available later.