← World of AI
Neural Networks
Liquid State Machines
A pool of spiking neurons whose rich dynamics make a signal easy to read off.
Feed a signal into a randomly connected reservoir of spiking neurons and its dynamics project the input into a high-dimensional space. Only a simple readout layer is trained; the reservoir itself is left alone.
Because training is cheap and the model is inherently temporal, the approach is of continuing interest for streaming signals and for neuromorphic hardware.
Also in Neural Networks
JOIN NOW
Begin the first module
It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.
Join any time · Build AI skills at your pace