Is it possible to apply some fundamental principles of quantum-computing to time series classi?cation algorithms? This is the initial spark that became the research question I decided to chase at the very beginning of my PhD studies. The idea came accidentally after reading a note on the ability of entanglement to express the correlation between two particles, even far away from each other. The test problem was also at hand because I was investigating on possible algorithms for real time bot detection, a challenging problem at present day, by means of statistical approaches for sequential classi?cation. The quantum inspired algorithm presented in this thesis stemmed as an evolution of the statistical method mentioned above: it is a novel approach to address binary and multinomial classi?cation of an incoming data stream, inspired by the principles of Quantum Computing, in order to ensure the shortest decision time with high accuracy. The proposed approach exploits the analogy between the intrinsic correlation of two or more particles and the dependence of each item in a data stream with the preceding ones. Starting from the a-posteriori probability of each item to belong to a particular class, we can assign a Qubit state representing a combination of the aforesaid probabilities for all available observations of the time series. By leveraging superposition and entanglement on subsequences of growing length, it is possible to devise a measure of membership to each class, thus enabling the system to take a reliable decision when a suf?cient level of con?dence is met. In order to provide an extensive and thorough analysis of the problem, a well-?tting approach for bot detection was replicated on our dataset and later compared with the statistical algorithm to determine the best option. The winner was subsequently examined against the new quantum-inspired proposal, showing the superior capability of the latter in both binary and multinomial classi?cation of data streams. The validation of quantum-inspired approach in a synthetically generated use case, completes the research framework and opens new perspectives in on-the-?y time series classi?cation, that we have just started to explore. Just to name a few ones, the algorithm is currently being tested with encouraging results in predictive maintenance and prognostics for automotive, in collaboration with University of Bradford (UK), and in action recognition from video streams.
Is it possible to apply some fundamental principles of quantum-computing to time series classi?cation algorithms? This is the initial spark that became the research question I decided to chase at the very beginning of my PhD studies. The idea came accidentally after reading a note on the ability of entanglement to express the correlation between two particles, even far away from each other. The test problem was also at hand because I was investigating on possible algorithms for real time bot detection, a challenging problem at present day, by means of statistical approaches for sequential classi?cation. The quantum inspired algorithm presented in this thesis stemmed as an evolution of the statistical method mentioned above: it is a novel approach to address binary and multinomial classi?cation of an incoming data stream, inspired by the principles of Quantum Computing, in order to ensure the shortest decision time with high accuracy. The proposed approach exploits the analogy between the intrinsic correlation of two or more particles and the dependence of each item in a data stream with the preceding ones. Starting from the a-posteriori probability of each item to belong to a particular class, we can assign a Qubit state representing a combination of the aforesaid probabilities for all available observations of the time series. By leveraging superposition and entanglement on subsequences of growing length, it is possible to devise a measure of membership to each class, thus enabling the system to take a reliable decision when a suf?cient level of con?dence is met. In order to provide an extensive and thorough analysis of the problem, a well-?tting approach for bot detection was replicated on our dataset and later compared with the statistical algorithm to determine the best option. The winner was subsequently examined against the new quantum-inspired proposal, showing the superior capability of the latter in both binary and multinomial classi?cation of data streams. The validation of quantum-inspired approach in a synthetically generated use case, completes the research framework and opens new perspectives in on-the-?y time series classi?cation, that we have just started to explore. Just to name a few ones, the algorithm is currently being tested with encouraging results in predictive maintenance and prognostics for automotive, in collaboration with University of Bradford (UK), and in action recognition from video streams.
This paper investigates the application of quantum-inspired neural networks (QINNs) to the problem of feature extraction from time-series data. Traditional neural networks, particularly recurrent neural networks (RNNs), often encounter challenges in effectively capturing complex temporal dependencies and correlations within time-series datasets. We propose a novel architecture based on quantum-inspired principles, leveraging concepts like superposition and entanglement to enhance the network's ability to model these intricate relationships. The QINN architecture incorporates multiple layers of interconnected nodes, where each node's state is influenced by a weighted sum of its inputs, mirroring the probabilistic nature of quantum mechanics. We introduce a new loss function designed to encourage the network to explore multiple potential solutions simultaneously, analogous to quantum superposition. The primary contribution of this work is the demonstration that quantum-inspired concepts can be effectively translated into a neural network architecture, potentially leading to improved feature extraction performance compared to conventional methods. We outline the architecture, the key mathematical formulations, and the rationale behind the design choices. The research highlights a promising direction for future development in time-series analysis and machine learning.
This paper introduces a novel approach to anomaly detection in time series data inspired by quantum mechanics, specifically quantum superposition and interference. Traditional anomaly detection methods often struggle with subtle deviations that may be masked within noisy data or require significant domain expertise to identify. Our method leverages the inherent properties of quantum states to represent time series data, enabling the generation of interference patterns that can amplify weak anomalies. We formulate the detection process as a measurement problem within a quantum framework, where the act of measurement itself can accentuate deviations from the expected quantum state. The core idea is to represent the time series as a superposition of possible states, and then observe the interference patterns resulting from this superposition. Anomalous events cause a shift in the interference pattern, which can be detected with higher sensitivity than traditional statistical methods. This approach offers the potential to significantly improve anomaly detection performance, particularly in scenarios with complex, high-dimensional time series data. The theoretical framework is presented, followed by a discussion of the key mathematical concepts and operational considerations. The paper concludes with a summary of the proposed method and its potential future directions.
Abstract Quantum Machine Learning was born during the past decade as the intersection of Quantum Computing and Machine Learning. Today, advances in quantum computer hardware and the design of simulation frameworks able to run quantum algorithms in classic computers make it possible to extend classic artificial intelligence models to a quantum environment. Despite these achievements, several questions regarding the whole quantum machine learning pipeline remain unanswered, for instance the problem of classical data representation on quantum hardware, or the methodologies for designing and evaluating quantum models for common learning tasks such as classification, function approximation, clustering, etc. These problems become even more difficult to solve in the case of Time Series processing, where the context of past historical data may influence the behavior of the decision-making model. In this piece of research, we address the problem of Time Series classification using quantum models, and propose an efficient and compact representation of time series in quantum data using amplitude embedding. The proposal is capable of representing a time series of length n in log2(n) l o g 2 ( n ) computational units, and experiments conducted on benchmark time series classification problems show that quantum models designed for classification can also outperform the accuracy of classic methods.
The convergence of quantum principles with classical artificial intelligence is reshaping computational paradigms in financial analytics. This paper presents a comprehensive framework for quantum-inspired computing, a class of algorithms that emulate quantum mechanics behaviors such as superposition, tunneling, and entanglement on classical hardware to address high-dimensional optimization and streaming challenges in finance. By reformulating problems like portfolio optimization, risk scoring, and derivative pricing within Quadratic Unconstrained Binary Optimization (QUBO) and tensor-network formulations, these methods achieve near-quantum performance using high-performance classical architectures. The proposed hybrid reference architecture integrates quantum-inspired solvers with real-time data ingestion, feature engineering, and governance layers, supporting transparent, adaptive, and auditable decision systems. We demonstrate that quantum-inspired algorithms can substantially reduce computation latency, improve convergence in dynamic markets, and enhance explainability in regulated environments. While challenges remain in scalability, benchmarking, and interpretability, these algorithms provide a pragmatic bridge toward future quantum-classical ecosystems, enabling financial institutions to operationalize quantum-era intelligence within current computational infrastructures.
Time series forecasting is a critical problem with applications in various fields, such as finance, energy, and environmental science. While classical machine learning methods have shown significant progress in this domain, the advent of quantum machine learning introduces a new perspective to address the complexities of time series prediction. In this research, we propose a novel Quantum Neural Network (QNN) approach for time series forecasting, leveraging the unique capabilities of quantum computing to capture intricate temporal dependencies and exploit quantum parallelism. By encoding time series data into quantum states and designing quantum circuits for processing, the QNN aims to achieve improved predictive accuracy compared to classical neural networks. Through extensive experiments on diverse time series datasets, we demonstrate the potential of our QNN framework and discuss the future prospects of quantum-powered time series prediction in real-world applications.
Time series forecasting remains a significant challenge in various domains, including finance, weather prediction, and industrial process control. Traditional neural networks, particularly recurrent neural networks (RNNs), often struggle to effectively capture the intricate temporal dependencies inherent in time series data. This paper proposes a novel approach leveraging quantum-inspired algorithms to optimize RNNs for improved time series forecasting performance. Specifically, we explore the utilization of quantum annealing techniques to adjust the weights within an RNN architecture. This approach mimics key quantum principles, such as superposition and interference, to potentially enhance the network's ability to represent and predict complex temporal patterns. The core claim of this work is that classical neural networks, particularly RNNs, are limited in their ability to model temporal dependencies. We introduce a mechanism where quantum-inspired algorithms, particularly quantum annealing, are employed to optimize the weights of RNNs. The underlying principles of superposition and interference are leveraged to capture more complex temporal patterns. The results demonstrate the potential of this quantum-inspired approach to achieving superior forecasting accuracy compared to conventional RNNs.