Source data for 5 main figures in "Resistive memory-based zero-shot liquid state machine for multimodal event data learning."

A novel neuromorphic computing paradigm for learning cross-modal event-driven signals that pushes limits for efficient real-time knowledge generalization and achieves zero-shot transfer learning for multimodal data.一种新颖的神经形态计算范式，旨在学习跨模态事件驱动信号，推动高效实时知识泛化的极限，并实现多模态数据的零样本迁移学习。