ZHAW: EVA Artificial Intelligence Seminar

I chose the paper Generative Adversarial Networks[1] from Ian Goodfellow, which I am going to review what the main points are and how it works. Intorduction Generative Adversarial Networks, or GANs for short, are an approach to generative modeling using deep learning methods. Generative modeling is an unsupervised learning task in machine learning that involves automatically discovering and learning the regularities or patterns in input data in such a way that the model can be used to generate or output new examples that plausibly could have been drawn from the original dataset.[1,2,3,4] How does it work? GANs consists of two networks, a Generator G(x), and a Discriminator D(x). They both play an adversarial game where the generator tries to fool the discriminator by generating data similar to those in the training set. The Discriminator tries not to be fooled by identifying fake data from real data. They both work simultaneously to learn and train complex data like audio, video or ima...

 Blog Post 2: Writing Style This second post is describing, what makes a writing output a good (or bad) piece of text, especially regarding the organization of the paper, wording without looking at the content.  I chose the paper Generative Adversarial Networks from Ian J. Goodfellow (https://arxiv.org/pdf/1406.2661.pdf), as I am very interested in this topic, my master thesis is about GANs and this paper is already familiar with me. It propose a new framework for estimating generative models via an adversarial process, in which the researchers simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. This paper is often cited and is also the starting point for anyone who learns about GANs, even though that paper is from 2014! Paper Title The title is short and sweet, at it is called "Generative Adversarial Nets". Everybody ...