photokan 0.2.0

Photonic KAN: Bridging PyTorch, KAN, and Q.ANT photonic hardware

PhotoKAN

Photonic Kolmogorov-Arnold Networks — bridging PyTorch · KAN · Q.ANT photonic hardware.

Phase 1 (CPU simulation) is fully functional. Q.PAL/NPU integration ships in Phase 2.

---

Why PhotoKAN?

Standard MLPs use fixed activations on nodes and linear weights on edges.
KANs invert this: learnable nonlinear functions sit on the edges, summed at nodes.

Photonic hardware is physically structured around edge-level nonlinear transforms — light through a waveguide produces exactly the kind of parametric nonlinear function a KAN edge needs. This is not an analogy; it is a direct structural match.

Published benchmarks show:

• 43% fewer parameters vs equivalent MLPs
• 46% fewer operations vs equivalent MLPs
• 30× energy efficiency gain on Q.ANT NPU vs CMOS

---

Installation

pip install photokan          # CPU simulation (no hardware required)
pip install photokan[qpal]    # + Q.ANT NPU support
pip install photokan[llm]     # + HuggingFace integration (Phase 3)
pip install photokan[dev]     # + development tools

---

Quick Start

import torch
import photokan as pk

# Works on CPU sim if no NPU — no code changes needed
model = pk.PhotoKAN(
    layer_sizes=[4, 16, 16, 1],
    activation='sine',   # 'sine' | 'fourier' | 'spline' | 'relu'
    backend='auto',      # auto-detects NPU, falls back to CPU
)

x = torch.randn(32, 4)
y = model(x)

# Standard PyTorch training
optimizer = torch.optim.Adam(model.parameters(), lr=1e-3)
loss = torch.nn.MSELoss()(y, torch.randn(32, 1))
loss.backward()
optimizer.step()

# Check what hardware is available
print(pk.available_backends())
# → {'cpu': True, 'cuda': True, 'qpal': False}

---

Activation Variants

Name	Formula	Best for	Photonic native
sine	Σ w·sin(f·x + p)	Periodic targets, photonic deployment	✅
fourier	a₀ + Σ [a·cos + b·sin]	Multi-frequency signals	✅
spline	B-spline basis	Non-periodic, high precision	Via LUT
relu	Σ w·ReLU(a·x + b)	Edge inference, speed	✅

---

Photonic Noise Simulation

Test accuracy against realistic hardware impairments before deploying to NPU:

sim = pk.PhotonicSimulator()
sim.set_hardware_profile('npu2')   # SNR=16dB, 8-bit

results = sim.sweep_snr(model, x_test, y_test,
                         snr_range=[8, 10, 12, 14, 16, 20])
sim.plot_snr_accuracy(results)

---

Architecture

User PyTorch model
    └── PhotoKAN / PhotoKANLayer   (nn.Module, drop-in)
            └── EdgeActivations    (sine / fourier / spline / relu)
                    └── QPALFunction (torch.autograd.Function)
                            ├── QPALBackend  → Q.ANT NPU via Q.PAL
                            └── SimBackend   → CPU physics simulation

---

Project Status

Phase	Features	Status
Phase 1	Activations, SimBackend, Layers, Utils	✅ Complete
Phase 2	Q.PAL integration, QPALBackend, gradient tests	🔜 Months 4–6
Phase 3	AOT compiler, LLM integration, arXiv paper	🔜 Months 7–12

---

Running Tests

pip install -e ".[dev]"
pytest                          # fast tests only
pytest -m slow                  # include convergence tests
pytest --cov=photokan           # with coverage

---

References

• Liu et al. (2024) — KAN: Kolmogorov-Arnold Networks
• Peng et al. (2024) — Photonic KAN via RAMZI (98% MNIST, 65× energy-area reduction)
• Reinhardt et al. (2024) — SineKAN
• Q.ANT NPU — https://qant.com/photonic-computing/

---

PhotoKAN v0.1 — Build the bridge. Light does the math.