Abstract
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.
| Original language | English |
|---|---|
| Article number | 3427 |
| Journal | Nature Communications |
| Volume | 13 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - Dec 2022 |
| Externally published | Yes |
UN SDGs
This output contributes to the following UN Sustainable Development Goals (SDGs)
-
SDG 7 Affordable and Clean Energy
ASJC Scopus subject areas
- General Chemistry
- General Biochemistry,Genetics and Molecular Biology
- General Physics and Astronomy
Fingerprint
Dive into the research topics of 'A framework for the general design and computation of hybrid neural networks'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver