Physical Realisation TRIZ Cases
- Optical Reservoir Computing with Waveguide Reflection Feedback
Waveguide reflection and nonlinear electro-optic conversion replace time-delay feedback, enabling faster, more scalable reservoir computing.
- Joint Neural Trajectory Prediction for Scene-Consistent Multi-Agent Paths
A policy-based neural model predicts joint multi-agent trajectories with scene consistency while cutting memory and computing load.
- Spintronic Neuron MTJ Structure for Leaky-Integrate-Reset
Electric-field-driven domain wall control in a segmented MTJ enables leaky-integrate-reset behavior plus global inhibition without hard magnets.
- Multi-Agent Trajectory Prediction Using Gibbs-Sampled Policy Networks
Grouped policy networks and Gibbs sampling generate scene-consistent multi-agent trajectories with lower compute and better interaction accuracy.
- RIS-Based Over-the-Air Neural Networks for Low-Power CNN Inference
RIS reflections emulate CNN convolution over the air, enabling low-power real-time inference on IoT devices without onboard processors.
- Neural Network Architecture Conversion for Fast Knowledge Transfer
Iterative layer conversion, random initialization, and fine-tuning transfer object recognition knowledge to smaller vehicle-ready neural networks.