gans
This semester I'm taking a course at UMBC called Causality in Machine Learning by Dr. Osman Gani [https://osmanii.github.io/]. So far, we've studied Simpson's Paradox, Causality and the Potential Outcomes Framework, Average Treatment Effect, Ignorability, Exchangability, Identifiability, Consistency, Structural Causal Models (i.
gans
Introduced by Goodfellow, et al. (Goodfellow) in 2014, a GAN consists of two functions, a generator and a discriminator, which are usually neural networks but can be any differentiable function. GANs are used to map data from one space to another; typically from a generated distribution \(p_g\) to an
gans
AutoGAN is an architecture search strategy developed by Gong, et al. in 2019 to find the most optimal Generator network architecture using reinforcement learning, trained to generate images from CIFAR-10 and STL-10. To understand how AutoGAN works requires an understanding of the basics of Neural Architecture Search (NAS). This post
dcgan
I've started experimenting with several GANs that will lead me into my independent studies this summer. So far I'm going to be studying the Goodfellow [https://arxiv.org/abs/1701.00160]"DCGAN". As my first step in researching the DCGAN, I learned fast about