EDEN-AlexNet-CIFAR-100 β EDEN Classic
Primary KPI: EAG (Energy-to-Accuracy Gradient) =
4.5587e-09ΞAcc/ΞJoules
Abstract
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 β maximising predictive power per Joule consumed.
Applied Technique: Phase 2 β EDEN Classic Energy-Aware Sparse Training
Profiling Environment
| Component | Specification |
|---|---|
| GPU | NVIDIA GeForce GTX 1080 Ti (11 GB VRAM, 250 W TDP) |
| CPU | Intel Xeon W-2125 (4 cores / 8 threads @ 4.00 GHz) |
| RAM | 63.66 GB System RAM |
| OS | Windows 10 |
| Dataset | CIFAR-100 β 60,000 images β 100 classes (32Γ32 px) |
π’ Green Delta Table
Comparing this model against the reference baseline (ResNet-50 equivalent)
| Metric | ResNet50 Baseline | AlexNet (EDEN) | Ξ |
|---|---|---|---|
| Accuracy | 0.9492 | 0.8933 | -5.59% |
| Total Energy (J) | 40,102,666 | 27,844,651 | 30.57% saved |
| COβ Emissions (kg) | 5.2913 | 3.6739 | β |
| EAG Score | β | 4.5587e-09 | ΞAcc/ΞJoules |
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 β Applied Phases
Phase 1 β Zero-Overhead Initialization: Dataset cached in System RAM.
Phase 2 β EDEN Classic: Energy-aware training loop on classic CNN architectures. Applies the same EAG early-exit criterion (EAG < Ξ³_EAG for 3 consecutive epochs β terminate), L1 sparsity penalty, and AMP to architectures like ResNet, VGG, AlexNet, DenseNet, InceptionV3, and UNet.
Training Statistics
| Metric | Value |
|---|---|
| Final Accuracy | 0.8933 (89.33%) |
| Total Energy Consumed | 27,844,651 J (7.7346 kWh) |
| Training Time | 0 s (0.00 hrs) |
| Estimated COβ | 3.6739 kg COβe |
| Training Log | test3\alexnet_EDEN_CIFAR100_stats.csv |
π Training Visualizations
Accuracy & Energy over Training
Green = accuracy (left axis) Β· Orange dashed = cumulative energy (right axis)
EAG Metric Trajectory
EAG = ΞAccuracy / ΞJoules β positive means learning more per Joule than baseline
Project-Wide Overview
All EDEN models: energy vs accuracy
Cite This Research
@misc{eden2025,
title = {Project EDEN: Energy-Driven Evolution of Networks},
author = {EDEN Research Team},
year = {2025},
note = {Hugging Face: Shanmuk4622},
url = {https://huggingface.co/Shanmuk4622}
}
Dataset used to train Shanmuk4622/EDEN-AlexNet-CIFAR-100
Evaluation results
- Accuracy on CIFAR-100self-reported0.893
- F1 Score on CIFAR-100self-reported0.893


