Explainable Neural Networks: Advancing Transparency in Deep Learning Models for Critical Applications
Keywords:
Explainable AI, Neural Networks, Model Interpretability, Transparency, Deep Learning, Critical SystemsAbstract
The remarkable performance of deep neural networks across diverse domains has precipitatedtheir integration into critical applications, including healthcare diagnostics, autonomoussystems, and financial forecasting. However, the inherent opacity of these models, often referred to as the "black box
References
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H.: Greedy layer-wise training of deep networks. In: Advances in Neural Information Processing Systems 19, pp. 153160. MIT Press, Cambridge, MA (2007).
Hinton, G.E., Osindero, S., & Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Computation 18(7), 1527–1554 (2006).
Downloads
Published
2018-12-08
How to Cite
Dr. Virender Khurana. (2018). Explainable Neural Networks: Advancing Transparency in Deep Learning Models for Critical Applications . Journal of Computational Analysis and Applications (JoCAAA), 25(6), 1–20. Retrieved from https://www.eudoxuspress.com/index.php/pub/article/view/3789
Issue
Section
Articles
