I have been messing with stacking multiple layers of Spatial Poolers together and see what happens. I originally thought this is a bad idea, but heck, stacked RBMs are a thing. Why not Stacked Spatial Pooler? The setup is simple. Train a stack of N SpatialPoolers with random values between 0~1. E…

Assuming that we have the stable representation forming in the association area, each node in the grid is following its own sequence as the saccades progress. Thinking of one of the most basic and highly tuned human skills, face recognition. The saccade scan pattern is highly stereotyped for any gi…

[image] Bitking: The feedback connections from the hex-grid act as a filter to focus this feature extraction; perception is active recall of learned features. Beyond lateral connections among Hex Grid minicolumns / cells, do you see any other feedback which could possibly be seen as reward fo…

[image] momiji: Beyond lateral connections among Hex Grid minicolumns / cells, do you see any other feedback which could possibly be seen as reward for correct categorisation of an input. As far as MNIST performance - that is with a single layer. I think you need an eyeball to look at differe…

[image] Bitking: And yes, hex-grids are attractor networks, just as you describe; simply proximal input and lateral input + inhibition. Why make it more complicated than necessary? I have nothing against it at all, its just proving difficult to figure out a process / structure / schema etc th…

I really do think that the deep learning people are showing the way here. You need a bunch of very simple well-defined operations that build to a solution. In this case, one of the joys of lateral connections is that varying the relations between the lateral connections and the inhibition gives yo…

I find the concept of stacked SPs troubling. How would that actually look in the biology? If you compare the reach of the dendrites from the cells that make up a mini-column it is about the same or smaller than the area of a winning mini-column in the pooling competition. This cell in this mini-col…

Very informative thanks especially the biology part. I do not know the answers of the questions though. [image] Bitking: I don’t see any possible mechanism for generalization. At least for me, I don’t see this exercise (stacked sp’s) is for generalizing patterns or detection. I see this as m…

[image] Bitking: I find the concept of stacked SPs troubling. How would that actually look in the biology? I agree with your concern, although I don’t entirely follow your argument. It’s very clear to me from the relevant paper here that the SP takes encoded sensor bit patterns as its input a…

@david.pfx @Bitking It seems this post is already past the idea of stacking spatial poolers and that it has been already demonstrated with interesting outputs (graphs above). I appreciate the suggestions/recommendations such as using another specialized component to recognize higher-order patterns …

Experimenting with stacking Spatial Poolers

Engineering

Jose_Cueto August 7, 2019, 2:24am 34

I found the relevent discussion about stacked sp - Network of SpatialPoolers

Topic		Replies	Views
The HTM Spatial Pooler: a neocortical algorithm for online sparse distributed coding Related Papers	48	4750	November 24, 2019
Basic Spatial Pooler Questions Numenta Theory spatial-pooling , question	25	5077	January 9, 2020
Network of SpatialPoolers Getting Started	15	1295	April 16, 2019
Stable-Enforced Pooling Tangential Theories hierarchy , spatial-pooling , grid , calvin , unsupervised-learnin	38	2321	June 18, 2018
HTM School Episode 7: Spatial Pooling Input Space & Connections YouTube spatial-pooling	33	3359	October 26, 2016

Experimenting with stacking Spatial Poolers

Related topics