Core Concepts
Abstract art patterns are effectively studied and generated using a modified Deep Convolutional GAN architecture.
Stats
"The model was trained upto 500 epochs."
"The Signal to Noise Ratio is 7.081."
"The distance between distributions is computed using L1 and L2 distances."
Quotes
"Generative Adversarial Networks consist of a generator and a discriminator."
"The proposed mDCGAN architecture is tailored for stable and enhanced art image generation."