EUVIMEDSkopri EUVIMED
Open access · CC BY-NC-ND 4.0

Flow Intelligence: Cross-Domain Deep Learning from Environmental Risk to Networked Community Systems

Mykhailo Pyrozhenko

Frontiers in Artificial Intelligence Research · 2025

DOI: 10.71465/fair383 ↗

At a glance

Journal article in Frontiers in Artificial Intelligence Research, 2025. Written by Mykhailo Pyrozhenko. The full text is freely available (open access, CC BY-NC-ND 4.0).

AstrattDettalji biblijografiċiCiteRelated studies

Abstract (original language)

This study explores a unifying perspective on artificial intelligence as flow intelligence—a learning paradigm that adapts to the continuity of time, structure, and uncertainty. Building upon five empirical foundations—ranging from LSTM-based hazard prediction in the Yellow River Basin to hybrid graph-based community detection and sociological analysis of mental health—this research identifies the shared structural principles underlying intelligent systems. Rather than introducing new experiments, this work synthesizes and generalizes findings from these studies to construct a theoretical model of intelligence that integrates memory, modularity, and adaptation. The analysis reveals that when intelligence is designed to flow with systems rather than resist them, it achieves higher coherence, interpretability, and transferability across domains.

Cite

APA

Pyrozhenko, M. (2025). Flow Intelligence: Cross-Domain Deep Learning from Environmental Risk to Networked Community Systems. Frontiers in Artificial Intelligence Research. https://doi.org/10.71465/fair383

Vancouver

Pyrozhenko M. Flow Intelligence: Cross-Domain Deep Learning from Environmental Risk to Networked Community Systems. Frontiers in Artificial Intelligence Research. 2025. doi:10.71465/fair383

BibTeX
@article{Pyrozhenko2025,
  author = {Pyrozhenko, Mykhailo},
  title = {Flow Intelligence: Cross-Domain Deep Learning from Environmental Risk to Networked Community Systems},
  journal = {Frontiers in Artificial Intelligence Research},
  year = {2025},
  doi = {10.71465/fair383}
}
Start for free →