CrX - Cognitive revolution X

Ø BrainX theory into CrX architecture

The brain processes input and allows it to travel throughout its pathways, regardless of where it originated (it doesn’t discriminate). Neurons serve as the paths for impulses to travel, with these paths branching in various directions, thereby altering the direction of the impulse at any given time. The impulse isn't consciously choosing its direction; rather, it changes direction due to the laws of physics and biological assistance. Several factors determine the direction of the impulse, and a regularly attended pathway has a higher probability of impulse transmission (thus, a higher likelihood of the impulse traveling this route). When impulses from the sides converge into the main impulse, it alters the direction of the main impulse. Of course, there is considerable noise in the brain – a challenge addressed by the concept that a large sum of correctly functioning impulses is sufficient for output (60% of correct impulses offset 40% of noise). The neuron's diverse paths and their changing direction abilities are equivalent to clusters that alter directions. Unlike the brain, the direction-changing in this architecture depends on factors like the presence of clusters around the chained neurons. Even though the brain doesn't discern the type of impulse it receives, it processes impulses because they change the physiology of neurons. It's the input and output regions in the brain that give representation to the impulse. Following the same principle, denser regions in the input region prioritize receiving impulses as they receive more impulses than non-denser regions (more impulses sustain the propagation of impulses in the brain, aiding in noise reduction). This is akin to the encoder and decoder having a probability density distribution function that assists in the destabilizing mechanism – a mechanism aimed at reducing noise in the model. Finally, the wiggle connection, where outputs are merged to yield a combined final output, is equivalent to the brain's formation of shortcuts between input and output, thereby bypassing the computational part. The network replicates the property of neurons clumping together into layers. Partitioning and clustering replicate the plasticity of neuron properties.

CrX architecture

In this page, I will be posting about the architecture of the CrX and its progress.

See the introductory video about this project here - "https://youtu.be/ij2qsPhYgJY"

Actually a small model was created based on this theory, and it was a success. i will start sharing the progress from this small model.

after scaling the model with more input routes to the brain, in other words i increased the number of senses to the model (brain). I got this output which was a good start, and I am going to scale it further to get a complete output.

I just realized with a small model, snake body-to-tail benchmark cant be achieved. as for achieving that benchmark -

1. the model should have to be bigger

2. presence of other senses like ears, voice should be present. as this senses will help the neurons to converge (this converging of neurons is not implemented in the current version of the model) helps in activating the nearby potential neurons. immature brain learns by senses help, after maturing the brain can generate its own assistance impulse by recursive ring loops to activate any pathway. as convergence is not implemented we cannot implement those senses. as they work well only if both are present. this current model using four eyes that act as a substitute for the other senses as they assist in activating the neurons like any other senses. convergence is not required for the eye senses impulses.

3. small models cannot predict or do something on their own as assistance is required a lot, they work well when they are made big.

currently i am confused what to do next, as i see no door to move forward. except asking seeking help from other people. i cannot do this all by myself, my work is done, my limited resource and time had led me to this situation and this act as constraint to make any progress. the foundational architecture was completed and tested, it was working fine. i will post the output image below...

this foundational architecture achieved

1. nearby activation of neurons by other nearby active neurons(assistance)

2. recursive loops to get the complete the output

what needs to get done?

1. scaling the model

2. implementing the convergence of nearby neurons & adding of other senses to the model

Different Intertwined neurons are more helpful in propagating the impulses, which i came to know when i was developing the CrX model.

From this journey, I learned that replicating the brain's processes is significantly more computationally expensive than anticipated. In the brain, everything is self-regulated—neurons operate autonomously when an impulse arrives, without requiring constant instructions. These neurons have pre-programmed functions to determine their next action in response to incoming stimuli.

However, when attempting to replicate this process in code, the entire system needs to be explicitly regulated and controlled. Each artificial neuron must be managed individually, as they lack the inherent autonomy of biological neurons.

One analogy I like to use is this: imagine replicating an entire village (Village 1) with its living people by creating another village (Village 2) populated with non-living entities that act like the living people in Village 1. The complexity of managing and simulating Village 2 highlights the challenge of replicating autonomous systems artificially.

Now, I am searching for a solution to this problem—how to enable artificial neurons to function autonomously. Unless I achieve this, computational demands will remain a significant barrier to completing this project.