Explosive neural networks via higher-order interactions in curved statistical manifolds — mentioned by westurner

Tue, 19 Aug 2025 02:39:14 GMT

Spiking transistors model non-linear change in state. Would spiking transistors be useful for physically realizing the "explosive" behavior modeled in "Explosive neural networks via higher-order interactions in curved statistical manifolds" (2025) https://arxiv.org/abs/2408.02326 "Synaptic and neural behaviours in a standard silicon transistor" (2025) https://www.nature.com/articles/s41586-025-08742-4 Are spiking transistors useful for this too?

Paper and discussion history. A mention is not an endorsement.

Explosive neural networks via higher-order interactions in curved statistical manifolds — mentioned by westurner

Mon, 18 Aug 2025 23:52:58 GMT

"Explosive neural networks via higher-order interactions in curved statistical manifolds" (2025) https://arxiv.org/abs/2408.02326 : > Abstract: [...] By leveraging a generalisation of the maximum entropy principle, we introduce curved neural networks as a class of models with a limited number of parameters that are particularly well-suited for studying higher-order phenomena. Through exact mean-field descriptions, we show that these curved neural networks implement a self-regulating annealing process that can accelerate memory retrieval, leading to explosive order-disorder phase transitions…

Paper and discussion history. A mention is not an endorsement.

Explosive neural networks via higher-order interactions in curved statistical manifolds · HackerPapers discussions

Explosive neural networks via higher-order interactions in curved statistical manifolds — mentioned by westurner

Explosive neural networks via higher-order interactions in curved statistical manifolds — mentioned by westurner