This story was originally published on HackerNoon at: https://hackernoon.com/improving-deep-learning-with-lorentzian-geometry-results-from-lhier-experiments.
With improved accuracy, stability, and speed of training, new Lorentz hyperbolic approaches (LHIER+) improve AI performance on classification and hierarchy task
Check more stories related to tech-stories at: https://hackernoon.com/c/tech-stories. You can also check exclusive content about #hyperbolic-deep-learning, #riemannian-optimization, #lorentz-manifold, #metric-learning, #curvature-learning, #computer-vision-architectures, #hyperbolic-neural-networks, #lorentz-space-neural-networks, and more.

This story was written by: @hyperbole. Learn more about this writer by checking @hyperbole's about page, and for more stories, please visit hackernoon.com.

This study proposes a whole set of enhancements for hyperbolic deep learning in computer vision, which have been verified by conducting extensive experiments on conventional classification tasks and hierarchical metric learning. An effective convolutional layer, a resilient curvature learning schema, maximum distance rescaling for numerical stability, and a Riemannian AdamW optimizer are among the suggested techniques that are included into a Lorentz-based model (LHIER+). With greater Recall@K scores, LHIER+ performs better on hierarchical metric learning benchmarks (CUB, Cars, SOP).