WiMi Develops Scalable Quantum Neural Network Technology

WiMi Hologram Cloud Inc. has announced the development of a Scalable Quantum Neural Network (SQNN) technology, announced in a press release. This innovative technology leverages multiple small quantum devices as quantum feature extractors, which work in parallel to extract local features from input data. These features are then combined into a quantum predictor through classical communication channels to complete classification tasks.

WiMi's SQNN aims to address the limitations of current quantum computing hardware by enabling collaborative work among multiple small quantum devices. This approach not only achieves classification accuracy comparable to traditional Quantum Neural Networks (QNN) but also optimizes the use of quantum computing resources and enhances data efficiency.

The core architecture of the SQNN system includes three main components: Quantum Feature Extractor, Classical Communication Channel, and Quantum Predictor. The implementation involves several steps such as data preprocessing, quantum encoding, sub-feature extraction, feature aggregation and classification, and parameter optimization and training. Experimental results show that SQNN improves training efficiency while maintaining classification accuracy similar to traditional QNNs.