"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 with multi-stability and hysteresis effects. Moreover, by analytically exploring their memory-retrieval capacity using the replica trick, we demonstrate that these networks can enhance memory capacity and robustness of retrieval over classical associative-memory networks [...]
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
"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 with multi-stability and hysteresis effects. Moreover, by analytically exploring their memory-retrieval capacity using the replica trick, we demonstrate that these networks can enhance memory capacity and robustness of retrieval over classical associative-memory networks [...]
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?