Neural Net (Dense)
binary · 36 views
binary
What It Is
Synthetic trained dense-layer weights --- Xavier init plus 50 momentum-smoothed gradient updates, L1-like shrinkage of small weights, and heavy-tailed outliers. An *untrained* layer is i.i.d. Gaussian (indistinguishable from noise); training imprints local correlation.
Interpretation
Standard analysis sees: aperiodic / broadband; high-complexity (noise-like). The atlas detects no named structure beyond this.
What standard analysis sees
tail heaviness0.76
asymmetry0.28
occupancy0.41
short-range corr0.31
long-range memory0.31
spectral colour0.75
periodicity0.06
complexity0.87
time-irreversibility0.44
volatility clustering0.16
multifractality0.31
dimensionality0.80
nonstationarity0.31
What the atlas adds
Nothing beyond the standard reading — this source’s structure is already captured by standard features; the atlas adds no named residual.
Composition
dtypeuint8
range[0, 255]
unique values232 / 16384
mean ± std127 ± 35.7
Render Gallery
.png)
Native > phase_plotraw
.png)
Native > timeseriesraw
.png)
Native > triple_latticeraw
.png)
Boltzmann > lag_map
.png)
Boltzmann > spin_grid
.png)
Cayley > default
.png)
Chladni > plate_bottom
.png)
Chladni > plate_top
_(centered)/signed_log_z/Neural_Net_(Dense).png)
Heisenberg (Nil) (centered) > signed_log_z
_(centered)/xy_path/Neural_Net_(Dense).png)
Heisenberg (Nil) (centered) > xy_path
.png)
Hodge–Laplacian > default
/barcode/Neural_Net_(Dense).png)
Inflation (Substitution) > barcode
/d_curve/Neural_Net_(Dense).png)
Inflation (Substitution) > d_curve
.png)
Information Theory > default
.png)
Julia Set > escape_histogram
.png)
Klein Bottle > default
.png)
Laplacian > default
.png)
Logarithmic Spiral > default
.png)
Möbius-S³ > mobius_cylinder
.png)
Möbius-S³ > s2_base_map
.png)
Ordinal Partition > default
/phi_spectrum/Neural_Net_(Dense).png)
Penrose (Quasicrystal) > phi_spectrum
.png)
Persistent Homology > barcode
.png)
Persistent Homology > h1_diagram
.png)
Predictability > default
.png)
Recurrence Quantification > default
.png)
Spectral Analysis > default
.png)
Spectral Graph > default
.png)
Spirograph > mode_spectrum
.png)
Spirograph > phasor_trajectory
.png)
Symplectic > flux_grid
.png)
Symplectic > phase_space
/default/Neural_Net_(Dense).png)
Ulam Spiral (Sacks) > default
/default/Neural_Net_(Dense).png)
Ulam Spiral (Square) > default
.png)
Visibility Graph > default
.png)
Wavelet Cascade > default
Atlas Position
| Nearest neighbor | Distance | |
|---|---|---|
| Gaussian Noise | 2.70 | cross-domain |
| Entanglement Entropy | 3.08 | cross-domain |
| Poisson Counts | 3.50 | cross-domain |
Which Geometries Light Up
This source does not rank extreme on any metric.
← / → within domain · ⇧← / ⇧→ alphabetical · ⇧← / ⇧→ inside an open render = same view across sources