Abstract
In this paper, I propose an efficient method of identifying important neurons that are related to an object’s concepts by mainly considering the relationship between these neurons and their object concept or class. I first quantify the activation values among neurons, based on which histograms of each neuron are generated. Then, the obtained histograms are clustered to identify the neurons’ importance. A network-wide holistic approach is also introduced to efficiently identify important neurons and their influential connections to reveal the pathway of a given class. The influential connections as well as their important neurons are carefully evaluated to reveal the sub-network of each object’s concepts. The experimental results on the MNIST and Fashion MNIST datasets show the effectiveness of the proposed method.
Funder
Deanship of Scientific Research, King Khalid University of Kingdom of Saudi Arabia
Subject
General Earth and Planetary Sciences
Reference24 articles.
1. Representation learning: A review and new perspectives;Bengio;IEEE Trans. Pattern Anal. Mach. Intell.,2013
2. Bau, D., Zhou, B., Khosla, A., Oliva, A., and Torralba, A. (2017, January 21–26). Network dissection: Quantifying interpretability of deep visual representations. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.
3. Bau, D., Zhu, J.Y., Strobelt, H., Zhou, B., Tenenbaum, J.B., Freeman, W.T., and Torralba, A. (2019, January 6–9). Gan dissection: Visualizing and understanding generative adversarial networks. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA.
4. Zeiler, M.D., and Fergus, R. (2014, January 6–12). Visualizing and understanding convolutional networks. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.
5. Dosovitskiy, A., and Brox, T. (2016, January 27–30). Inverting visual representations with convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献