Visualization System for Evolutionary Neural Networks for Deep Learning
- ORNL
Deep learning is actively used in a wide range of fields for scientific discovery. To effectively apply deep learning to a particular problem, it is important to select an appropriate network architecture and other hyper-parameters (at each layer). Evolving architectures and hyper-parameters using a genetic algorithm is one current approach to search the huge space of all possible configurations to find those more optimal for the problem. However, examining an evolutionary process and tuning the genetic algorithm are challenging, pushing most users to treat the process as a black box. To address this challenge, we propose a visualization system for evolutionary neural networks for deep learning. The key feature of our visualization system is to provide a visual analytics environment for evaluating a genetic algorithm in order to improve the underlying operations to reduce time to find good solutions. Our system is able to not only visualize how a genetic algorithm traverses its search space but also allows users to examine evolving networks in-depth to get insights to improve performance through interactive visualization components.
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 1606803
- Country of Publication:
- United States
- Language:
- English
Similar Records
SNNVis: Visualizing Graph Embedding of Evolutionary Optimization for Spiking Neural Networks
Optimizing deep learning hyper-parameters through an evolutionary algorithm. In: MLHPC '15 Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments, Article No. 4
Ramifications of Evolving Misbehaving Convolutional Neural Network Kernel and Batch Sizes
Conference
·
Sat Nov 30 23:00:00 EST 2024
·
OSTI ID:2573544
Optimizing deep learning hyper-parameters through an evolutionary algorithm. In: MLHPC '15 Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments, Article No. 4
Conference
·
Wed Dec 31 23:00:00 EST 2014
·
OSTI ID:1567643
Ramifications of Evolving Misbehaving Convolutional Neural Network Kernel and Batch Sizes
Conference
·
Wed Oct 31 20:00:00 EDT 2018
· IEEE/ACM Machine Learning in HPC Environments (MLHPC)
·
OSTI ID:1495999