An Optimized Convolutional Neural Network Architecture Based on Evolutionary Ensemble Learning
Source abstract
Abstract
Convolutional Neural Networks (CNNs) models succeed in vast domains. CNNs are available in a variety of topologies and sizes. The challenge in this area is to develop the optimal CNN architecture for a particular issue in ord... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Neural Networks and Applications · Video Surveillance and Tracking Methods · Machine Learning and Data Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (64)
Show source-provided references
1. Recent advances in convolutional neural networks10.1016/j.patcog.2017.10.013 ↗
2. Deep residual learning for image recognition
3. Going deeper with convolutions
4. Automatically designing CNN architectures using the genetic algorithm for image classification10.1109/TCYB.2020.2983860 ↗
5. Neural architecture search with reinforcement learning
6. Learning transferable architectures for scalable image recognition
7. Practical block-wise neural network architecture generation
8. Designing neural network architectures using reinforcement learning
9. Efficient architecture search by network transformation
10. Efficient neural architecture search via parameter sharing
11. B. Wang, Y. Sun, B. Xue and M. Zhang, “Evolving deep convolutional neural networks by variable-length particle swarm optimization for image classification,” arXiv: 1803.06492, pp. 1–8, 2018.10.1109/CEC.2018.8477735 ↗
12. A hybrid differential evolution approach to designing deep convolutional neural networks for image classification
13. Evolving image classification architectures with enhanced particle swarm optimization10.1109/ACCESS.2018.2880416 ↗
14. A comparison of particle swarm optimization and the genetic algorithm
15. A review of population-based meta-heuristic algorithms
16. A survey of swarm and evolutionary computing approaches for deep learning10.1007/s10462-019-09719-2 ↗
17. Designing neural networks through neuro-evolution10.1038/s42256-018-0006-z ↗
18. Feature selection based on genetic algorithm and support vector machine for intrusion detection system
19. IGD indicator-based evolutionary algorithm for many-objective optimization problems10.1109/TEVC.2018.2791283 ↗
20. Genetic CNN
21. A. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang et al., “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” arXiv: 1704.04861, pp. 1–9, 2017.
22. F. N. Iandola, S. Han, M. W. Moskewic, K. Ashraf, W. J. Dally et al., “Squeezenet: Alexnet-level accuracy with 50× fewer parameters and < 0.5 MB model Size,” arXiv: 1602.07360, pp. 1–13, 2016.
23. Lightweight convolution neural networks for mobile edge computing in transportation cyber physical systems10.1145/3339308 ↗
24. Gpipe: Efficient training of giant neural networks using pipeline parallelism
25. A EDEN: Evolutionary deep networks for efficient machine learning
26. Completely automated CNN architecture design based on blocks10.1109/TNNLS.2019.2919608 ↗
27. A genetic programming approach to designing convolutional neural network architectures
28. A novel automatic CNN architecture design approach based on genetic algorithm
29. Rectified linear units improve restricted Boltzmann machines
30. Batch normalization: Accelerating deep network training by reducing internal covariate shift
31. Dropout: A simple way to prevent neural networks from overfitting
32. A multi-level GA search with application to the resource-constrained re-entrant flow shop scheduling problem
33. Cyclical learning rates for training neural networks
34. Prechelt · Lecture Notes in Computer Science · 2012 · 1524 · 5310.1007/978-3-642-35289-8_5 ↗
35. Elitism-based compact genetic algorithms10.1109/TEVC.2003.814633 ↗
36. Elitism and distance strategy for selection of evolutionary algorithms10.1109/ACCESS.2018.2861760 ↗
37. P. Esfahanian and M. Akhavan, “GACNN: Training deep convolutional neural networks with genetic algorithm,” arXiv: 1909.13354, pp. 1–17, 2019.
38. Evolutionary convolutional neural networks: An application to handwriting recognition10.1016/j.neucom.2017.12.049 ↗
39. Fake news stance detection using stacked ensemble of classifiers
40. Reducing squeezenet storage size with depthwise separable convolutions
41. R. Srivastava, K. Greff and J. Schmidhuber, “Highway networks,” arXiv: 1505.00387, pp. 1–6, 2015.
42. CNNs and transfer learning for lecture venue occupancy and student attention monitoring
43. Skip connections eliminate singularities
44. Gradient based learning applied to document recognition10.1109/5.726791 ↗
45. A. Krizhevsky and G. Hinton, “Learning multiple layers of features from tiny images, vol. 1, Toronto, ON, Canada: University of Toronto, Technical Report, 2009.
46. Imagenet: A large-scale hierarchical image database
47. Choosing mutation and crossover ratios for genetic algorithms–-A review with a new dynamic approach10.3390/info10120390 ↗
48. Genetic algorithm-neural network (GANN): A study of neural network activation functions and depth of genetic algorithm search applied to feature selection10.1007/s13042-010-0004-x ↗
49. Adam: A method for stochastic optimization
50. T. DeVries and G. W. Taylor, “Improved regularization of convolutional neural networks with cutout,” arXiv: 1708.04552, pp. 1–8, 2017.
51. Mobilenetv2: Inverted residuals and linear bottlenecks
52. ShuffleNet: An extremely efficient convolutional neural network for mobile devices
53. Effnet: An efficient structure for convolutional neural networks
54. Adaptive convolutional kernels
55. An enhanced hybrid mobilenet
56. Convolutional neural networks with layer reuse
57. Densely connected convolutional networks
58. Xception: Deep learning with depth-wise separable convolutions
59. Polynet: A pursuit of structural diversity in very deep networks
60. Squeeze-and-excitation networks
61. M. Tan and Q. V. Le, “Efficientnet: Rethinking model scaling for convolutional neural networks,” arXiv: 1905.11946, pp. 1–10, 2019.
62. DARTS: Differentiable architecture search
63. SNAS: Stochastic neural architecture search
64. J. Fang, Y. Chen, X. Zhang, Q. Zhang, C. Huang et al., “EAT-NAS: Elastic architecture transfer for accelerating large-scale neural architecture search,” arXiv: 1901.05884, pp. 1–10, 2019.