Structural Analysis of Sparse Neural Networks
This work addresses the need for better understanding and optimizing neural network architectures for researchers in machine learning and neuroevolution, though it appears incremental as it builds on existing sparse network and structural analysis concepts.
The paper tackles the problem of predicting image classifier performance by analyzing the structural properties of sparse neural networks' underlying graphs, using a network science perspective and a technique to embed arbitrary Directed Acyclic Graphs into ANNs.
Sparse Neural Networks regained attention due to their potential for mathematical and computational advantages. We give motivation to study Artificial Neural Networks (ANNs) from a network science perspective, provide a technique to embed arbitrary Directed Acyclic Graphs into ANNs and report study results on predicting the performance of image classifiers based on the structural properties of the networks' underlying graph. Results could further progress neuroevolution and add explanations for the success of distinct architectures from a structural perspective.