These are chat archives for FreeCodeCamp/DataScience
discussion on how we can use statistical methods to measure and improve the efficacy of http://freeCodeCamp.com
Anyone not familiar with GANs, there's a short paper on it https://arxiv.org/abs/1406.2661 At the very least, the abstract clearly describes the "adversarial" part of the name
We propose a new framework for estimating generative models via an adversarial process, in which we 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.
apottr sends brownie points to @erictleung :sparkles: :thumbsup: :sparkles: