This model is part of Project EDEN (Energy-Driven Evolution of Networks), implementing the
E2AM (Energy Efficient Advanced Model) Framework. The goal is to shift AI benchmarking from
pure accuracy to Green SOTA — maximising predictive power per Joule consumed.
Comparing this model against the reference baseline (ResNet-50 equivalent)
Metric
ResNet50 Baseline
MobileViTv3 (EDEN)
Δ
Accuracy
0.9354
0.9798
+4.44%
Total Energy (J)
40,291,739
8,947,585
77.79% saved
CO₂ Emissions (kg)
5.3163
1.1806
—
EAG Score
—
-1.4172e-09
ΔAcc/ΔJoules
A positive EAG means this model learns more per Joule than the baseline.
A negative EAG indicates a trade-off where higher accuracy required more energy investment.
E2AM Algorithm — Applied Phases
Phase 1 – Zero-Overhead Initialization: Dataset pre-loaded into pinned System RAM to eliminate disk I/O power spikes.
Phase 2 – Progressive Unfreezing: Backbone frozen for the first E_unfreeze epochs (only the classification head trains). At E_unfreeze, all layers are unfrozen and the learning rate is decayed. Gradient accumulation over N micro-batches simulates large batch sizes without proportional VRAM cost, slashing power-draw spikes.
AMP (Automated Mixed Precision):torch.cuda.amp.autocast() halves GPU memory bandwidth, reducing energy per backward pass.
Sparse Regularisation: L1 penalty λ·Σ|W| applied to trainable weights, driving dead neurons to zero and enabling future pruning.
