Greetings. Its Saturday night and a new blog post from DataHulk.. Funny Funny name.. I came up with this name 12 years back .. when I get angry I work on data...!
It's been some time since I spoke about Neural Networks, GANs & Ricci Flow (Ricci Flow was an important geometric tool in solving Poincare Conjecture....). Please feel free to check out latest paper on Shannon entropy power on Riemannian manifolds and
Ricci flow - https://arxiv.org/pdf/2001.00410.pdf (Lot of hints to Information Geometry & Topology..)
Here are 3 interesting papers which came out since my talks & articles (apart from Melanie Weber's papers at Princeton on Big Data & Ricci Flow.
1. Zhejiang University - THOUGHTS ON THE CONSISTENCY BETWEEN RICCI FLOW AND NEURAL NETWORK BEHAVIOR - https://arxiv.org/pdf/2111.08410.pdf
2. Oxford University - Over-squashing, Bottlenecks, and Graph Ricci curvature - https://towardsdatascience.com/over-squashing-bottlenecks-and-graph-ricci-curvature-c238b7169e16
3. University of Cambridge - RicciNets: Curvature-guided Pruning of High-performance Neural Networks Using Ricci Flow - https://arxiv.org/abs/2007.04216
Here are 3 interesting papers which came out since my talks & articles (apart from Melanie Weber's papers at Princeton on Big Data & Ricci Flow.
1. Zhejiang University - THOUGHTS ON THE CONSISTENCY BETWEEN RICCI FLOW AND NEURAL NETWORK BEHAVIOR - https://arxiv.org/pdf/2111.08410.pdf
2. Oxford University - Over-squashing, Bottlenecks, and Graph Ricci curvature - https://towardsdatascience.com/over-squashing-bottlenecks-and-graph-ricci-curvature-c238b7169e16
3. University of Cambridge - RicciNets: Curvature-guided Pruning of High-performance Neural Networks Using Ricci Flow - https://arxiv.org/abs/2007.04216
The computational graph is pruned based on a node mass probability function defined by local graph measures and weighted by hyperparameters produced by a reinforcement learning-based controller neural network.
3 unique papers with 3 different ideas of using Ricci flow in deep learning.
3 unique papers with 3 different ideas of using Ricci flow in deep learning.
The 4th one which is very very unique is CONVERGENCE OF RICCI FLOW SOLUTIONS TO TAUB-NUT by Francesco de Giovanni - https://arxiv.org/pdf/2008.03969.pdf
It does not show the applications through deep learning yet but as amazing paper which might have some future applications in deep learning.
No comments:
Post a Comment