Haijing Tang
ABSTRACT
In recent years, as an important research hotspot in the field of artificial intelligence and machine learning, the convolutional neural network has made substantial breakthroughs and has been widely used. In order to better explore and understand its structure, more and more researchers have shifted the focus of their research to the visualization of convolutional neural networks. They learned from the neural network what features were studied. They applied it to parameter adjustment and optimization in the convolutional neural networks and achieved good results. In this paper, the basic structure of convolutional neural network is described first. Secondly, some commonly used volume and neural network models are introduced. Finally, the convolutional neural network visualization technology is evaluated.
- HUBEL D H, WIESEL T N. Receptive fields, binocular interaction, and functional architecture in the cat's visual cortex{J}. Journal of Physiology, 1962, 160 (1): 106--154.Google Scholar
Cross Ref
- FUKUSHIMA K. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position{J}. Biological Cybernetics, 1980, 36 (4): 193--202.Google ScholarCross Ref
- LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition{J}. Proceedings of the IEEE, 1998, 86 (11): 2278--2324.Google ScholarCross Ref
- SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition {EB/OL}. {2015-11-04}.Google Scholar
- SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions {C}// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2015: 1--8.Google Scholar
- HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition {EB/OL}. {2016-01-04}.Google Scholar
- Hsu S H, Bayarsaikhan B E. Factors influencing on online shopping attitude and intention of mongolian consumers, The Journal of International Management Studies, vol. 7, no. 2, pp. 167--176, 2012.Google Scholar
- Krizhevsky, A, Sutskever, I, Hinton, G: Imagenet classification with deep convolutional neural networks. In: NIPS 2012. Google ScholarDigital Library
- Zeiler, Matthew D and Fergus, Rob. Visualizing and understanding convolutional neural networks. arXiv preprint arXiv:1311.2901, 2013.Google Scholar
- KINGMA D P, BA J. Adam: A method for stochastic optimization, CoRR, vol. abs/1412.6980, 2014.Google Scholar
- GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation, IEEE Conference on Computer Vision and Pattern Recognition, 2014. Google ScholarDigital Library
- MASAYUKI, KOBAYASHI, MASANORI, et al. Generative Adversarial Network for Visualizing Convolutional Network{J}. IEEE 10th International Workshop on Computational Intelligence and Applications, 2017.Google Scholar
- SZEGEDY C, ZAREMBA W, SUTSKEVER I, et al. Intriguing properties of neural networks, 2014.Google Scholar
- LIU M, SHI J, LI Z, et al. Towards Better Analysis of Deep Convolutional Neural Networks, IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS VOL. 23, NO. 1--2017. Google ScholarDigital Library
- QIN Z, XU Z, DONG Q, et al.VoCaM: Visualization Oriented Convolutional Neural, 978-1-5386-3093-8, 2017.Google Scholar
- WEI D, ZHOU B, TRRALBA A, et al. Freeman. Understanding intra-class knowledge inside CNN, CoRR, vol. abs/1507.02379, 2015.Google Scholar
- MAHENDRAN A, VEDALDI A. Visualizing deep convolutional neural networks using natural pre-images, International Journal of Computer Vision, pp. 1--23, 2016. Google ScholarDigital Library
- IOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift, in Proceedings of the 32nd International Conference on Machine Learning (ICML), 2015, pp. 448--456. Google ScholarDigital Library
- JIA Y, SHELHAMER E, DONAHUE J, et al. Guadarrama, and T. Darrell.Caffe: Convolutional architecture for fast feature embedding, arXiv preprint arXiv:1408.5093, 2014.Google Scholar
Index Terms
- Evaluation of Visualization Methods' Effect on Convolutional Neural Networks Research
Recommendations
Research on improved wavelet convolutional wavelet neural networks
AbstractConvolutional neural network (CNN) is recognized as state of the art of deep learning algorithm, which has a good ability on the image classification and recognition. The problems of CNN are as follows: the precision, accuracy and efficiency of ...
Maxout neurons for deep convolutional and LSTM neural networks in speech recognition
We combine maxout neurons with convolutional and LSTM structures for DNNs.The optimal network structures and training strategies are explored for the models.Experiments are carried out for 6 languages on the IARPA Babel data sets.State-of-the-art ...
Scene text recognition using residual convolutional recurrent neural network
Text is a significant tool for human communication, and text recognition in scene images becomes more and more important. In this paper, we propose a residual convolutional recurrent neural network for solving the task of scene text recognition. The ...
Comments