Dr. Ema Puljak Bio: Ema Puljak is a Quantum Algorithms Expert at PlanQC, working on quantum and quantum-inspired machine learning for real-world applications. She completed a collaborative PhD between CERN, the Barcelona Supercomputing Center, and Universitat Autònoma de Barcelona, focusing on improving anomaly detection methods using quantum and tensor-network techniques for medical imaging and high-energy physics. Passionate about science communication, she regularly delivers accessible talks and tutorials on quantum computing, tensor networks, and quantum machine learning. TITLE: Friendly Introduction to Quantum and Quantum-Inspired Machine Learning Abstract: This talk introduces quantum and quantum-inspired machine learning from a practical perspective. We start with a brief overview of classical ML, then move to quantum-inspired approaches based on tensor networks, which already enable efficient representations and compression on classical hardware. Next, we cover quantum machine learning, including variational circuits, quantum kernels, and hybrid quantum–classical workflows, highlighting where quantum models may assist (rather than replace) classical ML. We close with real-world application outlooks for both paradigms and open questions around scalability, and future perspectives, including whether demonstrating quantum advantage should be the only goal of quantum machine learning.
Dr. Ema Puljak Bio: Ema Puljak is a Quantum Algorithms Expert at PlanQC, working on quantum and quantum-inspired machine learning for real-world applications. She completed a collaborative PhD between CERN, the Barcelona Supercomputing Center, and Universitat Autònoma de Barcelona, focusing on improving anomaly detection methods using quantum and tensor-network techniques for medical imaging and high-energy physics. Passionate about science communication, she regularly delivers accessible talks and tutorials on quantum computing, tensor networks, and quantum machine learning. TITLE: Friendly Introduction to Quantum and Quantum-Inspired Machine Learning Abstract: This talk introduces quantum and quantum-inspired machine learning from a practical perspective. We start with a brief overview of classical ML, then move to quantum-inspired approaches based on tensor networks, which already enable efficient representations and compression on classical hardware. Next, we cover quantum machine learning, including variational circuits, quantum kernels, and hybrid quantum–classical workflows, highlighting where quantum models may assist (rather than replace) classical ML. We close with real-world application outlooks for both paradigms and open questions around scalability, and future perspectives, including whether demonstrating quantum advantage should be the only goal of quantum machine learning.
In this tutorial, we will have a first look at variational quantum machine learning (QML), which combines parametrized quantum circuits as models with a classical optimization loop. We start with a brief overview of quantum computing, highlighting its potential as well as its current limitations. Next, using the popular QML framework PennyLane, we show how to build a quantum model and integrate it into standard TensorFlow- or Torch-based ML workflows. Finally, we address pros and cons of QML and discuss open challenges in the field.
Machine Learning (ML) has changed the way computers work by letting them learn from data and make smart choices. However, traditional ML techniques encounter scalability and efficiency constraints as datasets get larger and computational problems become more complicated[1]. These restrictions could be circumvented by the new paradigms that quantum computing offers by using entanglement and superposition [2], [3]. The combination of the Quantum computing with the Machine Learning is called the Quantum Machine Learning(QML), offers efficiency improvements, new algorithmic opportunities, and speedups in certain linear algebraic operations. So, this review dives deeply into quantum-classical algorithms, with a particular emphasis on the approaches like quantum neural network and quantum support vector machines. We examine computational complexity, architectural design, benchmarking findings, and real-world applications (such as optimization, cryptography, and classification). We also discuss important issues including scalability, data encoding, and noise, and we suggest future paths for error prevention and scalable structures.
This study aims to evaluate the effectiveness of quantum-inspired machine learning (QIML) techniques when applied to high-dimensional data processing problems. Instead of relying on quantum hardware, QIML uses concepts such as amplitude encoding and tensor networks to improve the efficiency of traditional models. We compared the performance of QIML models with traditional machine learning models on three real-world datasets in the fields of finance, medical diagnosis, and natural language processing. The study used metrics of accuracy, training speed, and generalization properties for comparison. Our results show that hybrid QIML models achieve up to a 10% improvement in accuracy and a 40% improvement in training speed compared to traditional models. We also discuss current limitations in scalability and computational cost and suggest future research directions for developing QIML as an effective tool for processing complex data.
Quantum machine learning (QML) has emerged as a promising interdisciplinary field that integrates principles of quantum computing with machine learning techniques to address complex computational challenges. By leveraging quantum phenomena such as superposition and entanglement, QML aims to enhance learning efficiency, improve model performance, and enable the exploration of high-dimensional feature spaces that are intractable for classical methods. This paper presents a comprehensive review of recent developments in QML, covering fundamental concepts, algorithmic taxonomies, data encoding techniques, implementation challenges, and real-world applications. Key approaches, including quantum support vector machines (QSVM), variational quantum circuits (VQC), and quantum neural networks (QNN), are systematically analyzed. Furthermore, critical challenges, including noisy intermediate-scale quantum (NISQ) limitations, barren plateaus, data encoding bottlenecks, and the lack of demonstrated quantum advantage, are discussed in detail. The review also highlights emerging applications in material informatics, energy systems, healthcare, and optimization problems. Finally, future research directions are outlined, emphasizing the need for advancements in quantum hardware, scalable algorithms, hybrid frameworks, and standardized benchmarking. This work aims to provide a structured perspective on the current state of QML and to identify opportunities in deploy it effectively in solve real-world problems.
This chapter provides a formal, self-contained exposition of quantum-inspired machine learning (QiML), a subfield focusing on applying ideas of quantum mechanics to the development of powerful classical algorithms. Our starting point is setting up a defensible taxonomy to dissociate QiML from actual quantum machine learning, and to describe its historical antecedents in simulated annealing and more recent dequantization of quantum algorithms. The highlights of the chapter pursue four central streams of inspiration systematically, namely: (1) quantum many-body physics is used to turn model and data into simple tensor networks; (2) quantum feature maps lead to randomized kernel methods, quantum inpainting, and quantum groups; (3) quantum numerical linear atomization algorithm (HHL) provides the template to develop fast linear solvers and randomized numerical linear algebra; and (4) quantum approximate optimization algorithm (QAOA) is used to talk about non-convex optimization heuristics. In every region, we sketch the supporting theory, provide concrete algorithms along with quasi-pseudocode and complexity example, and introduce theoretical guarantees. A large experimental section compares these approaches to classical baselines on standard data, as well as providing detailed case studies in resource-constrained ML, large-scale linear models, and combinatorial optimization. The chapter is rounded off by concluding with some practical hints and tips, a critical reflection on the ethical issues, and a discussion of open problems in the field, providing relevant literature to graduate students and practitioners in a well-brought-up and detailed piece of work.
Quantum-Inspired Machine Learning (QiML) is a subfield of Quantum Machine Learning (QML) that implements quantum mechanical principles using classical computational resources, without requiring quantum hardware. Despite growing interest, QiML is frequently treated as a subset of broader QML surveys, leaving a gap in unified, cross-domain coverage. This survey provides the first dedicated examination of QiML as a standalone field, reviewing literature from 2017 to 2025 across tensor network simulations, dequantized algorithms, and variational quantum circuit simulations. We propose a unified taxonomy spanning these families, survey empirical applications across diverse domains, and assess practical limitations and open problems. Our analysis reveals that algorithmic maturity and practical readiness vary considerably across QiML families, with domain-specific success patterns driven by differing structural assumptions. Fundamental open questions remain around scalability, data embedding, and the relationship between quantum inductive biases and learning efficiency. This survey serves as a reference for researchers seeking a structured understanding of QiML’s current landscape and future directions.