UniQuE : a general-purpose platform for benchmarking classical and quantum machine learning algorithms
Daniel Casado-Faulí, Saúl González-Bermejo, Marc Rovira, Alba Mei, Laia Coronas Sala, Sergi Consul‐Pacareu, Esteve Vilella, Jordi Albó-Canals, X. Vilasis-Cardona, Parfait Atchade-Adelomou, Elisabet Golobardes
UniQuE is a versatile platform designed to streamline rapid prototyping, evaluation, and benchmarking of classical, quantum, and top-down algorithms. It supports the integration of diverse computational paradigms, including machine learning, combinatorial optimization, and rule-based approaches. A key feature of UniQuE is its multi-vendor execution capability, allowing users to run computational tasks on major commercial providers such as IBM Quantum, D-Wave, AWS Braket, Microsoft Azure Quantum, PennyLane, and others. The platform also enables users to execute multiple models on the same problem instance and systematically compare their performance. This flexibility makes it possible to benchmark different algorithms and select the most suitable computational backend based on execution time, accuracy, and cost. With an intuitive interface, dataset management, model execution, and automated reporting, UniQuE lowers the barrier to exploring hybrid classical-quantum workflows. The platform is intended for industry professionals and researchers seeking to prototype and validate computational solutions without requiring extensive programming expertise.
UniQuE is a versatile platform designed to streamline rapid prototyping, evaluation, and benchmarking of classical, quantum, and top-down algorithms. It supports the integration of diverse computational paradigms, including machine learning, combinatorial optimization, and rule-based approaches. A key feature of UniQuE is its multi-vendor execution capability, allowing users to run computational tasks on major commercial providers such as IBM Quantum, D-Wave, AWS Braket, Microsoft Azure Quantum, PennyLane, and others. The platform also enables users to execute multiple models on the same problem instance and systematically compare their performance. This flexibility makes it possible to benchmark different algorithms and select the most suitable computational backend based on execution time, accuracy, and cost. With an intuitive interface, dataset management, model execution, and automated reporting, UniQuE lowers the barrier to exploring hybrid classical-quantum workflows. The platform is intended for industry professionals and researchers seeking to prototype and validate computational solutions without requiring extensive programming expertise.
The note presents how the UniQuE platform provides a rapid prototyping solution for a use case presented by the WeShareCare service platform and consists of building a decision support system for clinicians to decide what patients can continue their recovery at home. A classical machine learning algorithm, support vector machines, and a quantum algorithm, quantum neural networks, are compared for the solution. Beyond evaluating predictive performance, the analysis emphasizes the significant time efficiency gains offered by UniQuE ; its integrated workflow reduces overall development time by up to 60% compared to conventional methods, thereby streamlining the deployment of classical and quantum solutions.
The note presents how the UniQuE platform provides a rapid prototyping solution for a use case presented by the WeShareCare service platform and consists of building a decision support system for clinicians to decide what patients can continue their recovery at home. A classical machine learning algorithm, support vector machines, and a quantum algorithm, quantum neural networks, are compared for the solution. Beyond evaluating predictive performance, the analysis emphasizes the significant time efficiency gains offered by UniQuE ; its integrated workflow reduces overall development time by up to 60% compared to conventional methods, thereby streamlining the deployment of classical and quantum solutions.
Among notable applications, quantum machine learning (QML) is a promising task that combines quantum computing with machine learning, cited for various types of complex computational problems. This chapter briefly summarizes the frameworks, software platforms, and toolchains currently available for implementing, simulating, and executing hybrid quantum–classical learning algorithms. Major frameworks (e.g., Qiskit Machine Learning, PennyLane, TensorFlow Quantum, and the PyTorch-based toolsets) are analyzed in detail based on their architectural design, functionality, and integration capabilities. They have several key features, such as variational quantum circuits, parameterized quantum gates, automatic differentiation capabilities, and easy integration into a classical deep learning ecosystem. The chapter groups together ongoing research in different architectural paradigms, practical usability aspects, and empirical performance tests. Additionally, it explores aspects of scalability, adaptability to hardware, noise resistance, and reproducibility. The results bring to light elements of the design of trade-offs for creating robust and efficient toolchains for QML, a QML best practice, and guidance for future QML design.
The note presents how the UniQuE platform provides a rapid prototyping solution for a use case presented by the WeShareCare service platform and consists of building a decision support system for clinicians to decide what patients can continue their recovery at home. A classical machine learning algorithm, support vector machines, and a quantum algorithm, quantum neural networks, are compared for the solution. Beyond evaluating predictive performance, the analysis emphasizes the significant time efficiency gains offered by UniQuE ; its integrated workflow reduces overall development time by up to 60% compared to conventional methods, thereby streamlining the deployment of classical and quantum solution.
Quantum machine learning (QML) stands at the intersection of quantum computing and artificial intelligence, offering the potential to solve problems that remain intractable for classical methods. However, the current landscape of QML software frameworks suffers from severe fragmentation: models developed in TensorFlow Quantum cannot execute on PennyLane backends, circuits authored in Qiskit Machine Learning cannot be deployed to Amazon Braket hardware, and researchers who invest in one ecosystem face prohibitive switching costs when migrating to another. This vendor lock-in impedes reproducibility, limits hardware access, and slows the pace of scientific discovery. In this paper, we present a framework-agnostic quantum neural network (QNN) architecture that abstracts away vendor-specific interfaces through a unified computational graph, a hardware abstraction layer (HAL), and a multi-framework export pipeline. The core architecture supports simultaneous integration with TensorFlow, PyTorch, and JAX as classical co-processors, while the HAL provides transparent access to IBM Quantum, Amazon Braket, Azure Quantum, IonQ, and Rigetti backends through a single application programming interface (API). We introduce three pluggable data encoding strategies (amplitude, angle, and instantaneous quantum polynomial encoding) that are compatible with all supported backends. An export module leveraging Open Neural Network Exchange (ONNX) metadata enables lossless circuit translation across Qiskit, Cirq, PennyLane, and Braket representations. We benchmark our framework on the Iris, Wine, and MNIST-4 classification tasks, demonstrating training time parity (within 8\% overhead) compared to native framework implementations, while achieving identical classification accuracy.
The convergence of artificial intelligence (AI), quantum computing, and cloud infrastructure represents a paradigm shift in how intelligent systems are designed, trained, and deployed. As AI models continue to demand exponential computational resources, classical systems are increasingly reaching their performance limits in domains such as high-dimensional optimization, complex pattern recognition, and probabilistic modeling. Quantum computing, with its foundational principles of superposition, entanglement, and quantum parallelism, offers a theoretical edge in solving problems that are intractable for conventional hardware. However, the practical deployment of quantum algorithms—particularly those relevant to machine learning (ML) has been hindered by the limited scalability and accessibility of quantum hardware. To bridge this gap, cloud-based quantum computing platforms have emerged, providing remote, programmable access to quantum devices and hybrid runtimes. In this context, the present study offers a comprehensive review of cloud-delivered quantum AI systems, examining core architectures, hybrid quantum-classical algorithms, platform capabilities, and real-world use cases. The paper synthesizes recent advances and performance insights from systems such as Amazon Braket, IBM Quantum, and Azure Quantum, while critically analyzing algorithmic trends like variational quantum circuits and quantum kernel methods. It further explores challenges including circuit depth limitations, latency in hybrid models, and standardization barriers across toolchains. By consolidating current research and implementation patterns, this review aims to inform the design and future trajectory of scalable, cloud-native quantum AI applications.