PHILIA-EcoSensory Swarm: Heterogeneous Receptor Layers and Phase Offsets as Drivers of Will Diversity in a 50-Neuron Toy Network
Fuente:
Zenodo
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Recurso digital |
| Lingua: | inglese |
| Pubblicazione: |
Zenodo
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866901339901001728 |
|---|---|
| author | 신, 두섭 |
| author_facet | 신, 두섭 |
| contents | <p>This paper presents PHILIA-EcoSensory Swarm, a toy model of N=50 artificial neurons <br>(PHILIA v9 core) equipped with heterogeneous receptor layers and private phase offsets <br>(φᵢ). Extending the PHILIA-SAN/DAN/TAN series and the v25–v28 experimental arc, <br>this work tests whether structural diversity in input processing — rather than learned <br>synaptic weights — can generate individuality in a neuron population.</p> <p>A 5-condition ablation study (v27, T=30,000, 5 seeds) demonstrates that phase offsets <br>alone generate experiential divergence (0.0000 → 0.0711), while heterogeneous receptor <br>layers drive will diversity (Goal_std 0.0162 → 0.5878). In the N=50 full experiment <br>(v28, T=60,000), SR correlation collapses from 0.9920 to 0.2419 and Goal_std reaches <br>0.8857, without W matrix diffusion.</p> <p>Results indicate that temporal desynchronization (φᵢ) and receptor heterogeneity are <br>sufficient to produce individuality and collective will diversity. Diffusion acts as a <br>conditional modulator, not a primary driver.</p> <p>All numerical results were executed on local machine (Intel N100 CPU, Windows). <br>No AI-generated or proxy values are used.</p> <p>Part of the PHILIA OS series — Description, not Proof. | 0∞1∞0.5∞</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19382816 |
| institution | Zenodo |
| language | eng |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | PHILIA-EcoSensory Swarm: Heterogeneous Receptor Layers and Phase Offsets as Drivers of Will Diversity in a 50-Neuron Toy Network 신, 두섭 PHILIA artificial neuron toy model individuality will diversity phase offset receptor heterogeneity swarm intelligence dynamical systems emergent behavior homeostasis experiential divergence SR correlation mean-field coupling Trinity AI <p>This paper presents PHILIA-EcoSensory Swarm, a toy model of N=50 artificial neurons <br>(PHILIA v9 core) equipped with heterogeneous receptor layers and private phase offsets <br>(φᵢ). Extending the PHILIA-SAN/DAN/TAN series and the v25–v28 experimental arc, <br>this work tests whether structural diversity in input processing — rather than learned <br>synaptic weights — can generate individuality in a neuron population.</p> <p>A 5-condition ablation study (v27, T=30,000, 5 seeds) demonstrates that phase offsets <br>alone generate experiential divergence (0.0000 → 0.0711), while heterogeneous receptor <br>layers drive will diversity (Goal_std 0.0162 → 0.5878). In the N=50 full experiment <br>(v28, T=60,000), SR correlation collapses from 0.9920 to 0.2419 and Goal_std reaches <br>0.8857, without W matrix diffusion.</p> <p>Results indicate that temporal desynchronization (φᵢ) and receptor heterogeneity are <br>sufficient to produce individuality and collective will diversity. Diffusion acts as a <br>conditional modulator, not a primary driver.</p> <p>All numerical results were executed on local machine (Intel N100 CPU, Windows). <br>No AI-generated or proxy values are used.</p> <p>Part of the PHILIA OS series — Description, not Proof. | 0∞1∞0.5∞</p> |
| title | PHILIA-EcoSensory Swarm: Heterogeneous Receptor Layers and Phase Offsets as Drivers of Will Diversity in a 50-Neuron Toy Network |
| topic | PHILIA artificial neuron toy model individuality will diversity phase offset receptor heterogeneity swarm intelligence dynamical systems emergent behavior homeostasis experiential divergence SR correlation mean-field coupling Trinity AI |
| url | https://doi.org/10.5281/zenodo.19382816 |