Pure_Optical_CUDA / BENCHMARK_RESULTS.md
Agnuxo's picture
Upload 10 files
95c13dc verified
# Fashion-MNIST Benchmark Results
## Optical-Mycelial Neural Network
### Model Architecture
- **Type**: Optical-Evolutionary Neural Network
- **Technology**: C++/CUDA implementation
- **Novel Features**:
- Optical field modulation with FFT processing
- Evolutionary mycelial (fungi) masks
- Dynamic amplitude and phase transformations
### Training Configuration
- **Dataset**: Fashion-MNIST (28×28 grayscale images, 10 classes)
- **Training samples**: 60,000
- **Test samples**: 10,000
- **Epochs**: 10
- **Batch size**: 256
- **Learning rate**: 1e-3
- **Fungi count**: 128
- **Optimizer**: Adam
### Results
**Best Test Accuracy: 81.94%** (achieved at epoch 9)
#### Per-Epoch Results:
| Epoch | Test Accuracy |
|-------|---------------|
| 1 | 78.11% |
| 2 | 79.61% |
| 3 | 80.56% |
| 4 | 80.86% |
| 5 | 81.03% |
| 6 | 81.01% |
| 7 | 81.57% |
| 8 | 80.73% |
| 9 | **81.94%** |
| 10 | 81.69% |
### Technical Details
- **Loss Function**: Softmax Cross-Entropy
- **Data Format**: Binary float32 images, uint8 labels
- **Hardware**: NVIDIA GPU (CUDA 13.0)
- **Compiler**: Visual Studio 2022 + NVCC
### Model Innovation
This represents the first application of optical-evolutionary neural networks to Fashion-MNIST classification, demonstrating the potential of bio-inspired optical computing architectures for image classification tasks.
### Code Availability
Complete C++/CUDA source code available at: [Repository URL]
---
*Generated with Optical-Evolutionary Neural Network Technology*
*Date: September 17, 2025*