Structural Analysis of Sparse Neural Networks
arXiv:1910.07225 · doi:10.1016/j.procs.2019.09.165
Abstract
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.
arXiv comment23rd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems
References in corpus (6)
- Scikit-learn: Machine Learning in Python
- Statistical mechanics of complex networks
- Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science
- Random graph models for directed acyclic networks
- Analysing Neural Network Topologies: a Game Theoretic Approach
- Sparse Neural Networks Topologies