Overview
Explore the potential of generalised divergences in enhancing invariant neural networks in this 21-minute conference talk from GSI. Delve into the theoretical foundations and practical applications of using diverse divergence measures to improve the robustness and performance of neural network architectures designed for invariance. Gain insights into how these advanced mathematical concepts can be leveraged to address challenges in machine learning and pattern recognition tasks across various domains.
Syllabus
Can generalised divergences help for invariant neural networks?
Taught by
Conference GSI