The coding of longer sequences in HTM SDRs

[robf]

@complyue

@JarvisGoBrr

how exactly is information about sequences being represented and stored here?

For the record, I posse exactly the same question

You said it yourself Jarvis:

@JarvisGoBrr

word embeddings and the way they encode words meaning by context of surrounding words

So we’re agreed word embeddings work. The only problem is how to extract them from a network of sequences:

@JarvisGoBrr

the complicated bit seems to be exactly that, how do you cluster several sequences together like that, specifically, how do you cluster both past and future into a state that can be evoked by an single input. Thats what bogs me down

I start from the position that such sequences are related in the network by sharing (multiple) beginning and end points.

That’s the shape of the network.

If that’s the shape of the network, why shouldn’t we be able to tune the network to reveal that shape. It’s there. We just have to figure out how to project it out.

@DanML seemed to glimpse this, in an oblique way:

@robf

@DanML

@robf

You basically want self activation for a path.

This sounds more like graph analysis than a Spiking Neural Net. I don’t know how.

“Graph analysis” might be a good way to characterize this. I want to find clusters of paths in a graph which share beginning and end points.

So I want to do “graph analysis”, to find “embeddings”, which embeddings are well known as effective representations of both meaning and structure for language.

The only difference is I think the embeddings will contradict, and there will be an indefinite number of them. So I think they must be found ad-hoc at run time.

And a likely way to do that is by clustering using oscillations. Something which is also known to reveal tightly connected sub-graphs which are “embedded” within a broader graph.