Combining Neuro-Evolution of Augmenting Topologies with Convolutional Neural Networks
This work addresses a limitation in deep learning for researchers, but it is incremental as it builds on existing methods without presenting concrete results.
The paper tackles the problem of fixed convolutional network topologies by combining NeuroEvolution of Augmenting Topologies (NEAT) with Convolutional Neural Networks (CNNs) using ResNet blocks, but notes that the system requires further optimization due to the high computational demands of genetic algorithms.
Current deep convolutional networks are fixed in their topology. We explore the possibilites of making the convolutional topology a parameter itself by combining NeuroEvolution of Augmenting Topologies (NEAT) with Convolutional Neural Networks (CNNs) and propose such a system using blocks of Residual Networks (ResNets). We then explain how our suggested system can only be built once additional optimizations have been made, as genetic algorithms are way more demanding than training per backpropagation. On the way there we explain most of those buzzwords and offer a gentle and brief introduction to the most important modern areas of machine learning