Interesting, but this approach is still about scaling in size.
There are other more promising approaches that actually allow to reduce size of the network and have better performance: Closed-form continuous-time neural networks [1], or also known as liquid neural network.
They have been proved better in navigation (cars and even drones), with as little as 15 neurons in the network. The smaller scale not only makes it highly efficient, but also allows to better understand what the network is doing due to lower complexity.
They have been proved better in navigation (cars and even drones), with as little as 15 neurons in the network. The smaller scale not only makes it highly efficient, but also allows to better understand what the network is doing due to lower complexity.
[1] https://www.nature.com/articles/s42256-022-00556-7