Structural Analysis of Sparse Neural Networks

16 Oct 2019  ·  Julian Stier, Michael Granitzer ·

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.

PDF Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Neural Architecture Search MNIST Sparse Neural Network R2 0.9314 # 1

Methods


No methods listed for this paper. Add relevant methods here