Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology
Published in
International Conference on Learning Representa...(2018)External Links:
TL
TL;DR
This work proposes neural persistence, a complexity measure for neural network architectures based on topological data analysis on weighted stratified graphs and derives a neural persistence-based stopping criterion that shortens the training process while achieving comparable accuracies as early stopping based on validation loss.
Abstract
While many approaches to make neural networks more fathomable have been proposed, they are restricted to interrogating the network with input data. Measures for characterizing and monitoring structural properties, however, have not been developed. In this work, we propose neural persistence, a complexity measure for neural network architectures based on topological data analysis on weighted stratified graphs. To demonstrate the usefulness of our approach, we show that neural persistence reflects best practices developed in the deep learning community such as dropout and batch normalization. Moreover, we derive a neural persistence-based stopping criterion that shortens the training process while achieving comparable accuracies as early stopping based on validation loss.
References47 items
1
On the information bottleneck theory of deep learning
2
On Characterizing the Capacity of Neural Networks using Algebraic Topology
3
Geometry Score: A Method For Comparing Generative Adversarial Networks
4
Scalable and accurate deep learning with electronic health records
5