Liquid State Machine: How it works and how to use it?

Question

I am now learning about LSM (Liquid State Machines), and I try to understand how they are used for learning.

I am pretty confused about what I read over the web.

I'll write what I understood -> It may be incorrect and I'll be glad if you can correct me and explain what is true:

LSMs are not trained at all: They are just initialized with many "temporal neurons" (e.g. Leaky Integrate & Fire neurons), while their thresholds are selected randomly, and so the connections between them (i.e. not each neuron has to have a common edge with each of the other neurons).

If you want to "learn" that x time-units after inputting I, the occurrence Y occurs, you need to "wait" x time-units with the LIF "detectors", and see which neurons fired at this specific moment. Then, you can train a classifier (e.g. FeedForward Network), that this specific subset of firing neurons means that the occurrence Y happened.

You may use many "temporal neurons" in your "liquid", so you may have many possible different subsets of firing neurons, so a specific subset of firing neurons becomes almost unique for the moment after you waited x time-units, after inputting your input I

I don't know whether what I wrote above is true, or whether it is a total garbage.

Please tell me if this is the correct usage and targets of LIF.

Answer 1

Liquid State Machine and Echo State machines are complex topics that deal with computational neuroscience and physics, topics like chaos, dynamic action system, and feedback system and machine learning.

1. Most implementations of Liquid State Machines using the reservoir of neurons untrained.

2. You need to wait at least until you finish giving the input.

3. You can imagine that your liquid complexity is a kernel in SVM that tries to project the data points to some hyperspace.

For more details on SVM, studying Machine Learning would be quite beneficial.  

Hope this answer helps.