WiMi Developed a Quantum Computing-Based Feedforward Neural Network (QFNN) Algorithm

/EIN News/ -- Beijing, April 23, 2025 (GLOBE NEWSWIRE) -- WiMi Developed a Quantum Computing-Based Feedforward Neural Network (QFNN) Algorithm

BEIJING, Apr. 23, 2025––WiMi Hologram Cloud Inc. (NASDAQ: WIMI) ("WiMi" or the "Company"), a leading global Hologram Augmented Reality ("AR") Technology provider, announced the development of a Quantum Computing-Based Feedforward Neural Network (QFNN) algorithm aimed at overcoming computational bottlenecks in traditional neural network training. The core innovation of this algorithm lies in efficiently approximating the inner product between vectors while utilizing Quantum Random Access Memory (QRAM) to store intermediate computational values, enabling rapid retrieval.
WiMi's QFNN training algorithm relies on several key quantum computing subroutines, with the most critical components being the quantized feedforward and backpropagation processes. In classical neural networks, feedforward propagation is used to compute the activation values of input data, while backpropagation adjusts weights to minimize the loss function. WiMi's quantum algorithm provides exponential speedup in both stages, enabling neural networks to achieve convergence in significantly less time.
Quantum Feedforward Propagation: Classical feedforward propagation involves multiple matrix-vector multiplications. WiMi's quantum algorithm leverages quantum state superposition and coherence to perform these operations. Specifically, it encodes neuron weights and input data in quantum coherent states and completes matrix-vector operations through the evolution of quantum states. This approach can perform computations in logarithmic time, greatly reducing the computational load.
Quantum Backpropagation: In neural network training, error backpropagation (BP) is the most critical component. The BP algorithm involves computing the gradient of the loss function and propagating it back to earlier layers of the network to update weights. WiMi's quantum algorithm leverages quantum coherent states to compute gradients and accelerates gradient calculations using the Quantum Fourier Transform (QFT), enabling gradient updates that are quadratically faster than traditional methods.
Quantum Random Access Memory (QRAM): In classical neural network training, each weight update requires accessing and storing a large number of intermediate computation results. QRAM allows these intermediate results to be stored in quantum states and retrieved efficiently for subsequent calculations. The advantage of QRAM lies in its ability to avoid redundant computations and provide exponential speedup.
A core advantage of WiMi's quantum algorithm is its reduced computational complexity. The computational complexity of classical neural networks typically depends on the number of connections between neurons, whereas our quantum algorithm depends only on the number of neurons. This means that for a network with N neurons and M connections, the computational complexity of classical algorithms is typically O(M), while our quantum algorithm reduces it to O(N).
More intuitively, in large-scale neural networks, the number of connections often far exceeds the number of neurons, so this quantum algorithm achieves at least a quadratic speedup. This breakthrough has significant implications for training deep learning models, particularly when handling ultra-large-scale datasets, as it can substantially reduce training time.
Overfitting is a common issue in deep learning, where a model performs well on training data but generalizes poorly on test data. WiMi has discovered that quantum algorithms naturally exhibit inherent resilience to overfitting during training. This is due to the intrinsic uncertainty of quantum computing, which makes the training process resemble regularization techniques used in classical deep learning.
In WiMi's quantum algorithm, the superposition and coherence of quantum states introduce a degree of noise in each computation's results. While this noise is typically considered an error in classical computing, in the context of machine learning, it acts like a random perturbation that prevents the model from overfitting to the training data. As a result, this quantum neural network can naturally achieve better generalization without requiring additional regularization techniques.
WiMi's Quantum Feedforward Neural Network (QFNN) holds broad application prospects, particularly in scenarios with extremely high demands for computational speed and data scale, such as financial market analysis, autonomous driving, biomedical research, and quantum computer vision. Beyond direct applications on quantum computers, WiMi's research also lays the foundation for quantum-inspired classical algorithms. These classical algorithms draw on the design principles of QFNN and achieve similar computational complexity optimizations on traditional computers. Although these quantum-inspired classical algorithms incur an additional quadratic computational overhead compared to true quantum algorithms, they provide a transitional solution for the current era where quantum computers are not yet widely available, enabling businesses to experience the advantages of quantum algorithms in advance.
Quantum computing is reshaping the future of machine learning, and WiMi's QFNN quantum algorithm is a significant milestone in this trend. By efficiently leveraging the advantages of quantum computing, it not only accelerates neural network training but also enhances generalization capabilities, opening new directions for the development of deep learning. With the continuous advancement of quantum hardware, there is reason to believe that quantum neural networks will become a critical component of the machine learning field in the coming years, ushering artificial intelligence into a new era of computation.

About WiMi Hologram Cloud

WiMi Hologram Cloud, Inc. (NASDAQ:WiMi) is a holographic cloud comprehensive technical solution provider that focuses on professional areas including holographic AR automotive HUD software, 3D holographic pulse LiDAR, head-mounted light field holographic equipment, holographic semiconductor, holographic cloud software, holographic car navigation and others. Its services and holographic AR technologies include holographic AR automotive application, 3D holographic pulse LiDAR technology, holographic vision semiconductor technology, holographic software development, holographic AR advertising technology, holographic AR entertainment technology, holographic ARSDK payment, interactive holographic communication and other holographic AR technologies.

Safe Harbor Statements

This press release contains "forward-looking statements" within the Private Securities Litigation Reform Act of 1995. These forward-looking statements can be identified by terminology such as "will," "expects," "anticipates," "future," "intends," "plans," "believes," "estimates," and similar statements. Statements that are not historical facts, including statements about the Company's beliefs and expectations, are forward-looking statements. Among other things, the business outlook and quotations from management in this press release and the Company's strategic and operational plans contain forward−looking statements. The Company may also make written or oral forward−looking statements in its periodic reports to the US Securities and Exchange Commission ("SEC") on Forms 20−F and 6−K, in its annual report to shareholders, in press releases, and other written materials, and in oral statements made by its officers, directors or employees to third parties. Forward-looking statements involve inherent risks and uncertainties. Several factors could cause actual results to differ materially from those contained in any forward−looking statement, including but not limited to the following: the Company's goals and strategies; the Company's future business development, financial condition, and results of operations; the expected growth of the AR holographic industry; and the Company's expectations regarding demand for and market acceptance of its products and services.

Further information regarding these and other risks is included in the Company's annual report on Form 20-F and the current report on Form 6-K and other documents filed with the SEC. All information provided in this press release is as of the date of this press release. The Company does not undertake any obligation to update any forward-looking statement except as required under applicable laws.

Contacts
WiMi Hologram Cloud Inc.
Email: pr@WiMiar.com

ICR, LLC
Robin Yang
Tel: +1 (646) 975-9495
Email: WiMi@icrinc.com