新闻动态

成果发表于2022年6月14日《自然·通讯》

        结合脉冲神经网络和人工神经网络两者的优势来设计混合神经网络（hybrid neural networks, HNNs），是一种日益增长的趋势。这里，我们通过引入混合单元（hybrid units, HUs）作为连接端口，提出了一个用于混合神经网络的通用设计和计算框架。该框架不仅整合了计算范式的关键特征，还将它们解耦以提高灵活性和效率。混合单元是可设计和可学习的，以促进混合神经网络中混合信息流的传输和调制。研究通过三个案例证明该框架可以促进混合模型的设计。混合传感网络实现了多路径传感，并实现了高跟踪精度和能量效率。混合调制网络实现了分层信息抽象，使得能够对多个任务进行元连续学习。混合推理网络以可解释的、稳健和并行的方式执行多模态推理。这项研究推进了广泛的智能任务的跨范式建模。

A framework for the general design and computation of hybrid neural networks 

Rong Zhao, Zheyu Yang, Hao Zheng, Yujie Wu, Faqiang Liu, Zhenzhi Wu, Lukai Li, Feng Chen, Seng Song, Jun Zhu, Wenli Zhang, Haoyu Huang, Mingkun Xu, Kaifeng Sheng, Qianbo Yin, Jing Pei, Guoqi Li, Youhui Zhang, Mingguo Zhao & Luping Shi*

DOI：https://doi.org/10.1038/s41467-022-30964-7

    There is a growing trend to design hybrid neural networks (HNNs) by combining spiking neural networks and artificial neural networks to leverage the strengths of both. Here, we propose a framework for general design and computation of HNNs by introducing hybrid units (HUs) as a linkage interface. The framework not only integrates key features of these computing paradigms but also decouples them to improve flexibility and efficiency. HUs are designable and learnable to promote transmission and modulation of hybrid information flows in HNNs. Through three cases, we demonstrate that the framework can facilitate hybrid model design. The hybrid sensing network implements multi-pathway sensing, achieving high tracking accuracy and energy efficiency. The hybrid modulation network implements hierarchical information abstraction, enabling meta-continual learning of multiple tasks. The hybrid reasoning network performs multimodal reasoning in an interpretable, robust and parallel manner. This study advances cross-paradigm modeling for a broad range of intelligent tasks.