WiMi Hologram Cloud Inc. Develops Single-Qudit Quantum Neural Network Technology

WiMi Hologram Cloud Inc. has announced the development of single-qubit quantum neural network technology for multi-task design. This technology has significant implications for the integration of future quantum computing and artificial intelligence. The rise of quantum computing provides new possibilities for addressing the limitations of classical computing in training large neural networks, which often require billions of parameters and massive data center resources. WiMi's SQ-QNN technology uses the state space of a single high-dimensional qudit to directly handle multi-class classification tasks, reducing circuit depth and training overhead.

Key Takeaways:

• WiMi's single-qudit quantum neural network technology is designed for multi-task design and has extremely disruptive significance in the integration of future quantum computing and artificial intelligence.
• The technology uses a single high-dimensional qudit to directly handle multi-class classification tasks, reducing circuit depth and training overhead.
• SQ-QNN employs a hybrid training method that combines extended activation functions with the optimization framework of Support Vector Machines (SVM).
• The entire technical logic of WiMi's SQ-QNN can be divided into three levels: quantum state encoding, unitary evolution design, and hybrid training optimization.
• WiMi uses the Cayley transform of skew-symmetric matrices to construct unitary operators, ensuring mathematical stability and efficiency in quantum circuit implementation.
• The technology introduces a hybrid training method, combining extended activation functions with SVM optimization, to efficiently optimize network parameters and acquire global optimal solutions.

Statistics:

• The number of categories in multi-class classification problems can be up to $d$, with a $d$-dimensional qudit system constructed to carry data.
• Traditional neural networks often require billions of parameters and massive data center resources, leading to a sharp rise in power consumption and hardware costs.
• SQ-QNN achieves complex decision boundaries through a single-step evolution, significantly reducing circuit depth compared to multi-layer propagation in classical neural networks.
• Training large neural networks currently requires billions of parameters and massive data center resources, becoming a real bottleneck in the development of artificial intelligence.

Sources:

• WiMi Hologram Cloud Inc. press release dated October 20, 2025.
• WiMi Hologram Cloud Inc. website.
• GLOBE NEWSWIRE press release dated October 20, 2025.
• ICR, LLC and WIMI Hologram Cloud Inc. announcements dated October 20, 2025.