Journal of Experimental & Theoretical Artificial Intelligence
Mixed continuous/binary quantum-inspired learning system with non-negative least square optimisation for automated design of regularised ensemble extreme learning machines
Ahmad Mozaffari, Nasser L. Azad, Mahdi Emami, Alireza Fathi
In this paper, a hybrid quantum-inspired evolutionary algorithm (QIEA) is proposed to automatically design regularised ensemble extreme learning machines (EELMs). Quantum evolutionary computing is a relatively recent spot-lighted concept which takes advantage from both the evolutionary and quantum computing laws. In general, QIEAs have been proven to be really powerful for optimising complex engineering tasks. The fascinating trait of observation operator in QIEA enables us to transform the quantum bits to both the binary and continuous spaces. Here, the authors present a mix continuous/binary version of QIEA, to find out whether it is suited for designing regularised EELMs. Indeed, the design process of EELM is conducted at two different levels, i.e. hyper and low levels. At the low level, some novel criteria are presented in the form of penalty functions to enable the optimiser searching for parsimonious, compact and accurate regularised extreme learning machines, as individual components of the ensemble. At the hyper-level, the non-negative least square error optimisation technique is utilised to deterministically find the most eligible components for designing the ensemble. Through extensive numerical experiments, the authors demonstrate that the proposed method is really efficient for the automated design of EELM identifiers.
In this paper, a hybrid quantum-inspired evolutionary algorithm (QIEA) is proposed to automatically design regularised ensemble extreme learning machines (EELMs). Quantum evolutionary computing is a relatively recent spot-lighted concept which takes advantage from both the evolutionary and quantum computing laws. In general, QIEAs have been proven to be really powerful for optimising complex engineering tasks. The fascinating trait of observation operator in QIEA enables us to transform the quantum bits to both the binary and continuous spaces. Here, the authors present a mix continuous/binary version of QIEA, to find out whether it is suited for designing regularised EELMs. Indeed, the design process of EELM is conducted at two different levels, i.e. hyper and low levels. At the low level, some novel criteria are presented in the form of penalty functions to enable the optimiser searching for parsimonious, compact and accurate regularised extreme learning machines, as individual components of the ensemble. At the hyper-level, the non-negative least square error optimisation technique is utilised to deterministically find the most eligible components for designing the ensemble. Through extensive numerical experiments, the authors demonstrate that the proposed method is really efficient for the automated design of EELM identifiers.
This paper proposes a novel type of quantum-inspired evolutionary algorithm (QiEA) for numerical optimization inspired by the multiple universes principle of quantum computing, which is based on the concept and principles of quantum computing, such as a quantum bit and superposition of states. Numerical optimization problems are an important field of research with several applications in several areas: industrial plant optimization, data mining and many others, and although being successfully used for solving several optimization problems, evolutionary algorithms still present issues that can reduce their performances when faced with task where the evaluation function is computationally intensive. In order to address those issues the QiEA represent the most recent advance in the field of evolutionary computation. This work present some application about combinatorial and numerical optimization problems.
Quantum-Inspired Evolutionary Algorithms (QIEAs) represent a novel fusion of quantum computing principles and classical evolutionary strategies, offering a powerful approach to solving complex optimization problems. This chapter provides a comprehensive overview, detailing foundational concepts, implementation techniques, and potential applications of QIEAs. By leveraging quantum phenomena such as superposition and entanglement, QIEAs enhance the exploitation and exploration capabilities of traditional evolutionary algorithms (EAs), thus enabling an efficient search of vast solution spaces. The study examines key components of QIEA, including quantum encoding, rotation gates, and entanglement operations, and compares its performance with classical EAs. By analyzing real-life examples of combinatorial optimization problems (COPs) such as the minimum spanning tree (MST), traveling salesman problem (TSP), and graph coloring, the chapter demonstrates QIEA’s superior efficiency and solution quality. Despite implementation challenges, QIEA shows promise in various domains, including machine learning, finance, healthcare, telecommunications, and e-commerce. Future research directions are outlined, emphasizing the need for simplified quantum-inspired operators, hybrid quantum-classical systems, and interdisciplinary collaboration. This chapter highlights the transformative potential of QIEA, setting the stage for further advancements and applications in optimization and computational efficiency.
We investigate two modified Quantum Evolutionary methods for solving real value problems. The Quantum Inspired Evolutionary Algorithms (QIEA) were originally used for solving binary encoded problems and their signature features follow superposition of multiple states on a quantum bit and a rotation gate. In order to apply this paradigm to real value problems, we propose two quantum methods Half Significant Bit (HSB) and Stepwise Real QEA (SRQEA), developed using binary and real encoding respectively, while keeping close to the original quantum computing metaphor. We evaluate our approaches against sets of multimodal mathematical test functions and real world problems, using five performance metrics and include comparisons to published results. We report the issues encountered while implementing some of the published real QIEA techniques. Our methods focus on introducing and implementing new rotation gate operators used for evolution, including a novel mechanism for preventing premature convergence in the binary algorithm. The applied performance metrics show superior results for our quantum methods on most of the test problems (especially for the more complex and challenging ones), demonstrating faster convergence and accuracy.
A novel evolutionary algorithm based on quantum computing concepts is applied to engineering optimization problems. Quantum computing mimics behavior of atoms in processing information. Quantum inspired algorithm is a concept, which employs certain elements of quantum computing to use in a wider class of search and optimization problems. The main parts of a quantum-inspired algorithm are the qubits (quantum equivalent of bits) and the quantum gates. Qubits hold the information in a superposition of all the states, while the quantum gates evolve the qubit to achieve the desired objective, which is, in optimization the maximum or the minimum. The paper addresses the ability of the Quantum-Inspired Evolution Algorithm (QIEA) to solve practical engineering optimization problems. QIEA, which is developed by authors, is based on their previous work and it is extended to acquire the floating-point representation of the information. The RQIEA is tested on a four benchmark engineering optimization problems. The results showed that the new algorithm has the ability to compete and even overcome other well known methods.
Quantum computing combined with machine learning, is a promising emerging field for tackling problems that are extremely expensive or fundamentally infeasible for classical computers. Nonetheless, design of the optimal quantum circuit for machine learning is a major challenge, which can be attributed to the exponential search space of the quantum gate arrangement and unmatched structured design methods. To resolve this, our work introduces a novel automated framework for quantum architecture search (AQAS) that adopts both meta-learning and evolutionary algorithms to automatically learn, transfer, and optimize quantum circuit architectures to suit different machine learning tasks. Our strategy relies on meta-learning to introduce a learning scheme, i.e. it allows the AQAS system to generalize across distributions by learning from a shared structural and functional prior from the distribution of machine learning problems. This enables the approach to quickly home in effective quantum circuit implementations for new tasks with low data or retraining. At the same time, we use evolutionary algorithms– mimicking natural selection– to breed populations of quantum circuit architectures. These circuits are represented in genotypes, are varied under mutation and crossover, and are selected according to a fitness function that blends quantum resource utilization (e.g., depth, qubits) with task-specific performance (e.g., classification accuracy or loss). The architecture is realized in a mixed quantum-classical environment, with quantum circuits simulated on quantum simulators and/or Noisy-Intermediate-Scale-Quantum (NISQ) devices. We verify the effectiveness of our approach on a number of benchmarked datasets and tasks which range from quantum-aided image recognition, time series prediction to medical diagnostics. We demonstrate that AQAS can discover compact, high-performing quantum models, which generalize better and are computationally more efficient than the custom-built quantum models.
The design of autonomous quantum systems constitutes an entirely new paradigm for next-generation computing by having machine intelligence do the engineering work to build and optimise successful quantum architectures. We address the problem of self-optimizing quantum systems that perform adaptive control, circuit synthesis and decision making in both accurate and uncertain controllable environments via a two-pronged approach: Reinforcement Learning (RL) together with Evolutionary Strategies (ES). In this work, we find that reinforcement learning provides a general framework for sequential decision-making, where agents learn optimal policies from reward signals by interacting with quantum environments. Evolutionary strategies, which are based on ideas from biological evolution, provide an alternative to RL by performing global optimization of quantum circuit parameters and architectures using the standard canonical processes of mutation, selection and recombination. Recent developments in quantum technologies show, again, that machine learning tools (ML), especially RL can be very useful to optimize unavailable closed blow-ups related with quantity functions. Moreover, evolutionary optimization based hybrids with RL have demonstrated better performance on the complex multi-objective quantum problems due to balanced exploitation and exploration. In this paper, we provide an overview of a versatile framework for autonomous quantum system design that showcases example algorithmic architectures, hybrid machine learning models and real world applications in areas such as quantum control, quantum circuit synthesis and energy optimization. In addition, we discuss well-known obstacles such as the scalability problem, the noise sensitivity issue, barren plateaus of quantum optimization and computational complexity. Comparisons to traditional methods show that reinforcement learning (RL) when combined with evolutionary strategies enables a significant improvement in efficiency, adaptability, and robustness for quantum system design as supported by experimental studies and case analyses. Future research directions are then discussed, including quantum-native learning algorithms, multi-agent quantum reinforcement learning and hardware-aware optimization techniques