Deep Learning Concepts for Evolutionary Art

Abstract

A deep convolutional neural network (CNN) trained on millions of images forms a very high-level abstract overview of any given target image. Our primary goal is to use this high-level content information of a given target image to guide the automatic evolution of images. We use genetic programming (GP) to evolve procedural textures.We incorporate a pre-trained deep CNN model into the fitness. We are not performing any training, but rather, we pass a target image through the pre-trained deep CNN and use its the high-level representation as the fitness guide for evolved images. We develop a preprocessing strategy called Mean Minimum Matrix Strategy (MMMS) which reduces the dimensions and identifies the most relevant high-level activation maps. The technique using reduced activation matrices for a fitness shows promising results. GP is able to guide the evolution of textures such that they have shared characteristics with the target image. We also experiment with the fully connected "classifier" layers of the deep CNN. The evolved images are able to achieve high confidence scores from the deep CNN module for some tested target images. Finally, we implement our own shallow convolutional neural network with a fixed set of filters.Experiments show that the basic CNN had limited effectiveness, likely due to the lack of training. In conclusion, the research shows the potential for using deep learning concepts in evolutionary art. As deep CNN models become better understood, they will be able to be used more effectively for evolutionary art.

Pixel-Based Approach for Generating Original and Imitating Evolutionary Art

“…In particular, an interactive board was used to let the people directly interact with the agents [13]. There are also many approaches used efficient and autonomous methods such as deep learning, neural networks, and convolutional neural networks [14][15][16].…”

Image Evolution Using 2D Power Spectra

“…Recent work by Tanjil [40] uses ideas from deep learning to guide evolutionary image synthesis. A heuristic is proposed that enables activation nodes of a deep convolution neural network (trained for classification) to be identified for use by fitness evaluation.…”

Evolución de parámetros de optimización de redes neuronales profundas para el reconocimiento y clasificación de imágenes

“…Se han desarrollado técnicas heurísticas como en [60] llamada estrategia de matriz mínima media para determinar los nodos CNN de alto nivel más adecuados para la evaluación de la aptitud. Esta estrategia previa a la evolución determina los nodos comunes de CNN de alto nivel que muestran altos valores de activación para una familia de imágenes que comparten una característica de imagen de interés.…”