# brain: self-organized learning emerges from coherent coupling of critical neurons.

<< ️Deep artificial neural networks have surpassed human-level performance across a diverse array of complex learning tasks, establishing themselves as indispensable tools in both social applications and scientific research. >>

<< ️Despite these advances, the underlying mechanisms of training in artificial neural networks remain elusive. >>

<< ️Here, (AA) propose that artificial neural networks function as adaptive, self-organizing information processing systems in which training is mediated by the coherent coupling of strongly activated, task-specific critical neurons. >>

<< ️(AA) demonstrate that such neuronal coupling gives rise to Hebbian-like neural correlation graphs, which undergo a dynamic, second-order connectivity phase transition during the initial stages of training. Concurrently, the connection weights among critical neurons are consistently reinforced while being simultaneously redistributed in a stochastic manner. >>

<< ️As a result, a precise balance of neuronal contributions is established, inducing a local concentration within the random loss landscape which provides theoretical explanation for generalization capacity. >>

<< ️(AA) further identify a later on convergence phase transition characterized by a phase boundary in hyperparameter space, driven by the nonequilibrium probability flux through weight space. The critical computational graphs resulting from coherent coupling also decode the predictive rules learned by artificial neural networks, drawing analogies to avalanche-like dynamics observed in biological neural circuits. >>

<< ️(AA) findings suggest that the coherent coupling of critical neurons and the ensuing local concentration within the loss landscapes may represent universal learning mechanisms shared by both artificial and biological neural computation. >>

Chuanbo Liu, Jin Wang. Self-organized learning emerges from coherent coupling of critical neurons. arXiv: 2509.00107v1 [cond-mat.dis-nn]. Aug 28, 2025.

https://arxiv.org/abs/2509.00107

Also: brain, neuro, network, random, transition, ai (artificial intell) (bot), in https://www.inkgmr.net/kwrds.html 

Keywords: gst, brain, neurons, networks, randomness, transitions, ai (artificial intell) (bot), learning mechanisms, self-organized learning, artificial neural networks, deep learning, neuronal coupling, criticality, stochasticity, avalanche-like dynamics.

# life: the Age of hallucinatory artificial intelligence (AI); the beginning.

<< It’s well known that all kinds of generative AI, including the large language models (LLMs) behind AI chatbots, make things up. This is both a strength and a weakness. It’s the reason for their celebrated inventive capacity, but it also means they sometimes blur truth and fiction, inserting incorrect details into apparently factual sentences. >>

<< They sound like politicians, they tend to make up stuff and be totally confident no matter what. >> Santosh Vempala. ️

<< Chatbots err for many reasons, but computer scientists tend to refer to all such blips as hallucinations. It’s a term not universally accepted, with some suggesting ‘confabulations’ or, more simply, ‘bullshit’. The phenomenon has captured so much attention that the website Dictionary.com picked ‘hallucinate’ as its word of the year for 2023. >>️

<< Because AI hallucinations are fundamental to how LLMs work, researchers say that eliminating them completely is impossible. >>️

Nicola Jones. AI hallucinations can’t be stopped — but these techniques can limit their damage. Nature. 637, 778-780. Jan 21,  2025. 

https://www.nature.com/articles/d41586-025-00068-5

Also: ai (artificial intell) (bot), nfulaw, in https://www.inkgmr.net/kwrds.html 

Keywords: life, ai, artificial intell, LLMs, bot, nfulaw

# ai-bot: Cybloids − Creation and Control of Cybernetic Colloids.

FIG. 11. Particle clusters formed for different parameters of the feedback potential.

AA << present an idea to create particles with freely selectable properties. The properties might depend, for example, on the presence of other particles (hence mimicking specific pair or many-body interactions), previous configurations (hence introducing some memory or feedback), or a directional bias (hence changing the dynamics). Without directly interfering with the sample, each particle is fully controlled and can receive external commands through a predefined algorithm that can take into account any input parameters. This is realized with computer-controlled colloids, which (AA) term cybloids - short for cybernetic colloids. >>

<< For a single particle, this programming can cause subdiffusive behavior or lend activity. For many colloids, the programmed interaction potential allows to select a crystal structure at wish. Beyond these examples, (AA) discuss further opportunities which cybloids offer. >>️

Debasish Saha, Sonja Tarama, et al. Cybloids − Creation and Control of Cybernetic Colloids. arXiv: 2408.00336v1 [cond-mat.soft]. 

https://arxiv.org/abs/2408.00336

Also: ai (artificial intell), bot, colloids, in https://www.inkgmr.net/kwrds.html 

Keywords: AI, Artificial Intell, BOT, AI-BOT, colloids, cybernetic colloids, cybloids