A quantum neural network for sequential data analysis in machine learning

K Thirupathi Reddy, K Raghupathi, Srujan Vannala

Yifan Sun, Boyuan Sun, Jiameng Tian +1 more

Machine learning holds fundamental computational significance due to the increasing demand for efficient solutions to complex tasks in data analysis, pattern recognition, and optimization, which are essential for addressing the multifaceted challenges of modern society. As the volume of data proliferates at an unprecedented rate, the need for more powerful machine learning strategies becomes increasingly evident. Quantum neural networks (QNNs) represent an emerging and transformative research field that seeks to harness the unique principles of quantum mechanics to enhance the capabilities of machine learning algorithms. This survey examines various QNN approaches, including fully connected QNNs, quantum convolutional neural networks, equivariant QNNs, quantum Hopfield networks, quantum Boltzmann machines, quantum reservoir computing, and composite networks for quantum reinforcement learning, quantum generative learning, and quantum transfer learning. We summarize the relevant investigations on their performance, including learning accuracy, training time, and resource requirements, etc. Each QNN type has unique strengths and weaknesses, offering diverse solutions for different applications.

Pramoda Medisetty, Leela Krishna Kumar Pallapothu, Poorna Chand Evuru +3 more

Machine learning that combines the power of graph neural networks has its own significance in developing quick report analysis for various dynamic data which traditional statistical models may not be able to accomplish. Alongside the use of Quantum Computing in Neural Networks have become increasingly important over the years due to their ability to learn and process complex patterns. The Importance of QNN lies in the approaches it follows like entanglement, interference multiple super positional states, parallel computing, and backpropagation trainings which cannot be possible for Classical Neural Networks to work with. Also, the QNN, GNN integrates with the Quantum Machine Learning techniques like PennyLane that acts as an OpenShift framework to execute the optimized, trained algorithms for quick computational outcomes. This paper contains the use of Quantum Neural Networking, Quantum Machine Learning.

Yanan Li, Zhimin Wang, Rongbing Han +6 more

Yanan Li, Zhimin Wang, Rongbing Han +6 more

Jincheng Zhang

Quantum Neural Networks (QNNs) hold tremendous potential for revolutionizing machine learning, particularly in complex data analysis and pattern recognition. However, training QNNs can be computationally expensive and require significant expertise in network architecture and optimization. This paper proposes a novel approach to QNN training – Adaptive Tensor Representation Learning (ATRL) – which dynamically adjusts the tensor representation of the network based on the input data's unique characteristics. We demonstrate that ATRL significantly improves model performance across a range of datasets compared to traditional training methods. The method leverages the inherent properties of quantum neural networks to automatically learn and refine the tensor structure, fostering a more robust and adaptable model. This research addresses a critical bottleneck in QNN development, offering a pathway towards more efficient and effective training.