This paper introduces an optical spiking neural network that utilizes optical rogue-wave statistics as a programmable firing mechanism. It demonstrates how phase-engineered caustics enable robust, passive thresholding, thereby harnessing extreme-wave phenomena for scalable and energy-efficient neuromorphic photonic inference.

This paper introduces CogniSNN, a novel Spiking Neural Network (SNN) paradigm that incorporates Random Graph Architectures (RGA) to address the limitations of traditional, rigid SNN designs. CogniSNN enhances neuron-expandability, pathway-reusability, and dynamic-configurability, leading to improved performance, robustness, and continual learning capabilities in multi-task scenarios.

This paper introduces the Spiking-Quantum Data Re-upload Convolutional Neural Network (SQDR-CNN), a novel architecture that enables joint training of spiking neural networks and quantum circuits. The model achieves competitive accuracy with significantly fewer parameters than state-of-the-art SNN baselines, showcasing the potential of hybrid neuromorphic and quantum systems for efficient machine learning.

This paper proposes a novel hybrid temporal-8-bit spike coding method that integrates bit-plane decompositions with temporal coding principles to enhance Spiking Neural Network (SNN) performance. It demonstrates competitive and often improved results on various computer vision benchmarks when trained with surrogate backpropagation.