Selection Instability
The Selection Instability task evaluates whether an evolved Dynamic Neural Field (DNF) architecture can perform decision-making through competitive dynamics.
The desired behaviour is:
- Multiple external stimuli are presented simultaneously, inducing multiple peaks in the input field.
- The input field maintains a multi-peak representation during stimulus presentation.
- Activity is transmitted to the output field.
- The output field resolves competition via winner-take-all dynamics, stabilizing a single dominant peak.
- After stimulus offset, both fields relax back to baseline.
This task tests the emergence of selection and decision-making as a dynamical property, rather than as an explicit symbolic operation.
The highest-fitness solutions typically converge to a near-minimal topology, though with greater variability than detection or memory:
-
Fields: 2 (input → output)
-
Hidden fields: usually 0, occasionally 1–2
-
Connections: typically 1 feedforward coupling, with optional additional connections
-
Dynamics:
- Input field: Mexican-hat kernel supporting stable multi-peak activation
- Output field: Gaussian kernel enabling competitive suppression and selection
The figure above shows:
- Blue: activity during stimulus presentation
- Red: activity after stimulus removal
The output field selects a single stimulus location while suppressing competitors, implementing winner-take-all behavior.
Analysed 100 runs; 100 reached the fitness threshold (100.0% success, threshold = 0.950)
- Mean: 13.00
- Median: 9.00
- Std: 12.26
- Mean convergence rate (fitness gain/gen): 0.0347
- Mean fitness improvement/gen: 0.0357
- Hidden fields (mean ± std): 0.27 ± 0.56
- Enabled connections (mean ± std): 1.45 ± 1.07
| label | run | value |
|---|---|---|
| Highest max fitness | 2026-01-24 19h08m33s | 0.981938 |
| Lowest max fitness | 2026-01-24 18h55m02s | 0.950192 |
| Fastest to threshold | 2026-01-24 23h07m48s | 1.0 |
| Slowest to threshold | 2026-01-24 20h15m51s | 73.0 |
| Most hidden fields | 2026-01-24 19h08m33s | 2.0 |
| Most enabled connections | 2026-01-24 19h54m56s | 7.0 |
This section reports detailed statistics from the evolutionary run that produced the highest-fitness solution for the Selection Instability task.
Final generation: g = 11
- Best fitness: 0.9803
- Target fitness: 0.950
- Average fitness: 0.7336
Overall run statistics
- Max best fitness: 0.9803 (reached at generation 11)
- Mean best fitness over run (AUC): 0.7756
- Mean average fitness over run (AUC): 0.7020
- Longest stagnation period: 2 generations
- Target fitness first reached: generation 11 (best fitness ≈ 0.9803)
Final generation (g = 11)
- Species: 118
- Active species: 93
Across run
- Total distinct species created: 63
- Species extinct by final generation: 2
- Average species per generation: 26.25
- Average active species per generation: 23.67
- Max active species in a generation: 93 (at g = 11)
Species lifetime & size
- Average species lifespan: 3.13 generations
- Longest-lived species: 0 (lifespan 11)
- Average max members per species: 42.65
- Average offspring per species: 158.73
Final generation (g = 11)
- Avg genome size: 7.22
- Avg field genes: 3.36
- Avg connection genes: 3.86
Growth over run
- Genome size change: +5.22 (≈ +0.475 / gen)
- Field genes change: +1.36 (≈ +0.124 / gen)
- Connection genes change: +3.86 (≈ +0.351 / gen)
Ratios
- Avg connections per field (final gen): 1.15
-
Field kernels:
- Gaussian: 22 497 (89.4%)
- Mexican-hat: 2 674 (10.6%)
-
Interaction kernels:
- Gaussian: 11 241 (97.9%)
- Mexican-hat: 240 (2.1%)
Generation: 11 Fitness: 0.9803
| Field | Role | Kernel type | Field parameters | Kernel parameters |
|---|---|---|---|---|
| nf 1 | Input | Mexican-hat | h = -4.20, τ = 55.66 | A_exc = 17.34, σ_exc = 5.00, A_inh = 28.55, σ_inh = 5.88, A_glob = -0.08 |
| nf 2 | Output | Gaussian | h = -3.42, τ = 31.69 | A = 3.00, σ = 1.55, A_glob = -0.13 |
| Interaction gene | From → To | Kernel parameters |
|---|---|---|
| gk cg 1-2-1 | nf 1 → nf 2 | A = 3.00, σ = 2.09, A_glob = 0.00 |
selection.mp4
- Winner-take-all behavior emerges from strong inhibitory Mexican-hat dynamics in the input field
Despite the population exploring highly complex genomes, the best solution collapses back to a compact, interpretable architecture, reinforcing neat-dnfs’ bias toward minimal sufficiency.
Selection Instability is substantially more demanding than detection or memory:
- Convergence is slower and more variable.
- Some (very little) runs require additional structure beyond the minimal two-field topology.
- Nevertheless, winner-take-all decision-making reliably emerges from continuous DNF dynamics.
This task marks the transition from representation to choice.