generative adversarial networks

In 2014, Ian Goodfellow, then at OpenAI, published his seminal paper, titled “Generative Adversarial Networks”1, detailing how competition between generator and discriminator functions, approximated by neural networks, can train the generator to produce realistic images. In this article I will be discussing the theory behind this idea, my own implementation in Julia (mirroring the network structure in Goodfellow’s original paper), and show some of the images I was able to get out....

January 30, 2022 · 6 min

using Julia to do web based interactive plotting

So you want inline interactive plots in your blog posts? But you don’t want to learn javascript and there wasn’t an obvious way to embed matplotlib? If your comfortable with (or willing to learn) Julia, there is a simple and elegant solution! Makie.jl is a julia plotting package with a lot of functionality, including a backend system consisting of WGLMakie and JSServe which provides a way to embed makie plots—including 3d visualizations—right into html and inserted into markdown jekyll blog posts....

December 20, 2021 · 3 min