Portal de Periódicos da CAPES

“GAS” Instead of “Liquid”: Which Liquid State Machine is Better?

2022; Springer Nature; Linguagem: Inglês

10.1007/978-3-031-19032-2_49

1860-9503

Mikhail Kiselev, Andrey Lavrentyev,

Neural dynamics and brain function

The crucial feature of liquid state machines (LSM) is memory which is necessary to the convert spatio-temporal input patterns and their sequences scattered in time into multidimensional representation in the form of instant neuronal activity. In this work, we utilize a methodology for exact estimation of LSM memory ability and to find parameters of the LSM “liquid” (the chaotic spiking neural network) optimal from viewpoint of memory depth using genetic algorithm. We applied this technique to chaotic networks of leaky integrate-and-fire neurons with adaptive threshold. The result of the optimization was rather unexpected – best memory was demonstrated by an ensemble of unconnected neurons more corresponding to metaphor of “gas” than “liquid”. This result compels to revise the traditional view on liquid state machines and efficiency of spiking neural networks playing the role of “liquid” in it.