Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Intelligent Neural Networks: From Layered Architectures to Graph-Organized Intelligence

About

Biological neurons exhibit remarkable intelligence: they maintain internal states, communicate selectively with other neurons, and self-organize into complex graphs rather than rigid hierarchical layers. What if artificial intelligence could emerge from similarly intelligent computational units? We introduce Intelligent Neural Networks (INN), a paradigm shift where neurons are first-class entities with internal memory and learned communication patterns, organized in complete graphs rather than sequential layers. Each Intelligent Neuron combines selective state-space dynamics (knowing when to activate) with attention-based routing (knowing to whom to send signals), enabling emergent computation through graph-structured interactions. On the standard Text8 character modeling benchmark, INN achieves 1.705 Bit-Per-Character (BPC), significantly outperforming a comparable Transformer (2.055 BPC) and matching a highly optimized LSTM baseline. Crucially, a parameter-matched baseline of stacked Mamba blocks fails to converge (>3.4 BPC) under the same training protocol, demonstrating that INN's graph topology provides essential training stability. Ablation studies confirm this: removing inter-neuron communication degrades performance or leads to instability, proving the value of learned neural routing. This work demonstrates that neuron-centric design with graph organization is not merely bio-inspired -- it is computationally effective, opening new directions for modular, interpretable, and scalable neural architectures.

Antoine Salomon• 2025

Related benchmarks

TaskDatasetResultRank
Character-level Language Modelingtext8 (test)
BPC1.705
128
Language ModelingPenn Treebank (PTB) word-level (val)
Perplexity207.2
11
Character-level Language ModelingWikiText-2 (val)
PPL (Validation)3.61
3
Showing 3 of 3 rows

Other info

Follow for update