Conference proceeding
Towards Searching Efficient and Accurate Neural Network Architectures in Binary Classification Problems
2021 International Joint Conference on Neural Networks (IJCNN), v 2021-
18 Jul 2021
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
In recent years, deep neural networks have had great success in machine learning and pattern recognition. Architecture size for a neural network contributes significantly to the success of neural networks. In this study, we optimize the selection process by investigating different search algorithms to find a neural network architecture size that yields the highest accuracy. We apply binary search on a very well-defined binary classification network search space and compare the results to those of linear search. We also propose how to relax some of the assumptions regarding the data set so that our solution can be generalized to any binary classification problem. We report a 100-fold running time improvement over the naive linear search when we apply the binary search method to our data sets in order to find the best architecture candidate. By finding the optimal architecture for any binary classification problem quickly, we hope that our research contributes to discovering intelligent algorithms for optimizing architecture selection in machine learning.
Metrics
20 Record Views
Details
- Title
- Towards Searching Efficient and Accurate Neural Network Architectures in Binary Classification Problems
- Creators
- Yigit Alparslan - Drexel UniversityEthan Jacob Moyer - Drexel UniversityIsamu Mclean Isozaki - Drexel UniversityDaniel Schwartz - Drexel UniversityAdam Dunlop - Drexel UniversityShesh Dave - Drexel UniversityEdward Kim - Drexel UniversityIEEE
- Publication Details
- 2021 International Joint Conference on Neural Networks (IJCNN), v 2021-
- Publisher
- IEEE
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science; College of Computing and Informatics
- Web of Science ID
- WOS:000722581701073
- Scopus ID
- 2-s2.0-85116421562
- Other Identifier
- 991019169661204721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
Source: SDGs in the Output
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Hardware & Architecture
- Engineering, Electrical & Electronic