[Korrelan]

If you reverse engineer the human ocular system (ignoring focal distance and depth of field, etc) this is an approximate procedural/ algorithmic representation of the (colour) retinal schema projected onto V1.

Multiple interpolated (receptive field ranges) resolutions are recognised at the same time through a polar centric schema, a low resolution periphery graded to a high resolution fovea. So for any high resolution information there is also a low resolution spatial element of the surrounding overall area/ scene. The schema of the retina provides a top down influence for free, so… if the rough outline is cat shaped and fovea detects feline’s eyes… it’s probably a cat.

The small image (bottom left of left window) represents the whole of the circular/ retina, spatially arranged into a Cartesian format which is roughly analogous to the V1 spatial map. Rotational invariance simply moves the overall image detail left or right, scale invariance moves the image detail up/ down.

Eye movements and saccades are learned/ made relative to this polar map, so for any unrecognised object/ patch in the periphery the fovea can instantly traverse to focus on that region.

For textures or repeating patterns like fur, the center high res fovea recognises the texture, and all other joined/ un-bordered retinal locations with the same/ similar colour/ contrast attributes are assumed to be the same material, show by the colour fill.

https://youtu.be/m6Pw7qugpKE

If this retinal modality/ output is then translated into neural code, even foetal models can instantly recognise simple objects after one exposure.

https://youtu.be/uZYO6lCPQYs

The extra spikes for some objects on the pattern lock are caused by extreme similarities.  The system has noticed (from its point of view, not ours) similarities in composition, colour, etc.  Prior to being shown these objects the system had learned to ‘see’ from scratch, it learned to differentiate and categorise the visual sensory stream, its then able to recognise new objects from memory.  The spikes are an accumulation of episodic memories firing that encode/ remember the salient qualities of each object.



 

[Korrelan]

Closing post on project thread… My AI-Dream… has become an AI-Reality…

Thanks all for following my project, AI-Dreams has been my ‘lounge’, a place where I could relax, reflect and contemplate away from the usual harshness of the internet, both the forum and the good natured members have provided the environment I required, and helped me to bring my project to fruition... in the coming years… keep an eye out for the ‘blue K’.

Thanks and cheers.

 

https://www.youtube.com/user/korrelan

End

[Korrelan]

OK... Thanks for the hard work keeping the forum going... I guess I'll keep posting

This is the equivalent of learning 80 'words' 5000 characters long... in 3 minutes.

No big deal for a modern PC but... this very small section of my models neocortex can recognise any of the complete 80 * 5000 instantly, or any length sub-section of the 5k pattern, at any location within the 5k wide constant stream within 0.002 sec. It's limited to 80 patterns for testing (7K neurons and 30K synapse).

It shows my optimal dendrite branching modality so far, growing from scratch... AI savant mode lol.

https://youtu.be/oRLhtwvMWUE

 

[Korrelan]

Its been brought to my attention that some peers find my videos confusing and are not understanding/ reading the ‘Pattern Lock’ graphs correctly.  So I’ve done some redesigning, hopefully making them clearer. The new graph can be seen in the video below, and the following paragraphs are the description/ explanation I intend to use…

The ‘Pattern Lock’ graph shows both the input and the output/ best guess.  There are 80 colour coded inputs/ patterns (left to right) and the small white square moving along the scale indicates the current number of the input being injected into the model.  The moving green rectangle shows the models output/ best guess for each input pattern and should ideally match/ line-up with the input.  The height of the peak shows the confidence in the pattern match.

Each input represents 5000 human faces/ parameters.

https://youtu.be/UcUY0qlwGhc

Is this clear? Any suggestions?

 

[HS]

The general idea makes sense. One question, how many unique pieces are in a column of 5000 pieces so that the net can recognize any length subsection?

[Korrelan]

To show the graph peak clearly, for this demo (above) I've tried to make all the patterns as unique as possible, so no face set is duplicated, though it is finding some similarities, shown by the low response/ confidence peaks.

The model can learn to recognise any length pattern/ sub pattern embedded in any length stream.

Normally pattern similarities in pattern groups show up as extra peaks, like in this object recognition demo, the extra peaks show its finding a commonality with another object, could be the general shape/ outline, colour, etc.  Each object is tuned to a specific location along the graph.

https://youtu.be/uZYO6lCPQYs

This brings up a good point actually... the green rectangle is just showing the strongest pattern response, on some of my vids the graph is showing features not single/ specific recognition... this needs more thought.

 

[MikeB]

each colour represents neuron clusters recognising a single word in the paragraph

Are the coloured neuron clusters spread out in the brain model in any particular order? Is there a method for which goes where? EG. Specific thinking goes on in one part of the brain... and whether they're linked to theoretical body parts like on the homunculus brain-body chart?

[Korrelan]

@MikeB... Appologies for the delay...

They are ordered by the system, relevant to their sensory relevance for the current task. The efferant axons from the Homunculus/ nervous system  model are connected to the motor cortex as part of the initial model design.


Second attempt at an explanation for the pattern lock graph...

Most of my videos include some version of my pattern lock graph; this is (hopefully) a clear explanation of its functions.

The purpose of the graph is show that specific sets of output neurons are firing in response to a given sensory/ input stimulus.  The output neurons/ networks are grouped into 80 colour coded blocks represented by the colour gradient (x axis) on the graph. The height of a peak (y axis) corresponds to the confidence or the number of neurons firing within that group.
 
The graph can also show (x axis) the current test pattern being injected into the model, the small white square moving along the scale shows the current pattern number (1-80)

The graph shows the firing rate of all the output neurons at the same time, and ideally for most testing purposes only one high/ strong peak should accompany any single input pattern.

Video demonstration index…

0:06 Inject 98% white noise, this totally saturates the connectome with white noise to demonstrate the various output neuron groups firing & registering on the graph.

0:15 Start decreasing noise to sensory equivalent level (50%) to show the connectome model begin to ignore/ filter out the white noise, ie no high peaks on the graph.

0:35 Start Injecting the (1-80) learned patterns.  Now a peak can be clearly seen following/ matching the input pattern number. The peak is slightly in front of the pattern because the connectome is predicting the next pattern in the sequence.  Max-P just highlights the maximum peak.

0:47 Stop the noise to show clean response of connectome to just the sensory input without the white noise interference.

0:58 Clicking on the graph sets/ changes the pattern number, clicking back shows GTP inertia.  Although the input pattern has been changed/ moved back, the current recognised pattern keeps running for a few ms.

Note: If you find this explanation confusing or have any questions please comment.

https://youtu.be/MjN8q5cKNTc

 

[Korrelan]

Part of my neural research is about gaining insights, by building a connectome and running countless simulations I sometimes get lucky… I know this looks weird, but this seems to be how the connectome optimally builds the ocular system (slowed down for viewer).

It’s a graded theta timed, phased access to a scalable interpolated matrix of retinal inputs (center surrounds) that accumulate in V1 to give an overall ‘image’.

It’s top down; each wider view is used limit/ tune/ focus recognition to the next finer, higher rez/ detail level. Ie if the wider scene is mostly blue then there’s no point considering trees.  The recognition process (GTP) is focused by the increasing resolution.

The initial wider angles are used for spatial awareness, orientation, location, etc, global recognition at each scale solves several problems, monocular distance judgement, scale invariance, tunnel vision, etc; see my other videos for rotational invariance solution.

https://youtu.be/AobB_oTj67I