China
Africa
Explore chapters and articles related to this topic
Quantum Artificial Intelligence for the Science of Climate Change
Published in Thiruselvan Subramanian, Archana Dhyani, Adarsh Kumar, Sukhpal Singh Gill, Artificial Intelligence, Machine Learning and Blockchain in Quantum Satellite, Drone and Network, 2023
Manmeet Singh, Chirag Dhara, Adarsh Kumar, Sukhpal Singh Gill, Steve Uhlig
AI on quantum computers is known as QAI and holds the promise of providing major breakthroughs in furthering the achievements of deep learning. NASA has Quantum Artificial Intelligence Laboratory (QuAIL) which aims to explore the opportunities where quantum computing and algorithms address machine learning problems arising in NASA’s missions [21]. The JD AI research centre announced that they have a 15-year research plan for quantum machine learning. Baidu’s open-source machine learning framework Paddle has a subproject called paddle quantum, which provides libraries for building quantum neural networks [22]. However, for practical purposes, the integration of AI and quantum computing is still in its infant stage. The use of quantum neural networks is developing at a fast pace in the research labs; however, pragmatically useful integration is in its infant stages [23,24]. The current challenges to industrial-scale QAI include how to prepare quantum datasets, how to design quantum machine learning algorithms, how to combine quantum and classical computations and identifying potential quantum advantage in learning tasks [25]. In the past five years, algorithms using quantum computing for neural networks have been developed [26,27]. Just as the open-source TensorFlow, PyTorch and other deep learning libraries stimulated the use of deep learning for various applications, we may anticipate that software, such as TensorFlowQ (TFQ), QuantumFlow and others, already in development will stimulate advances in QAI.
Quantum Multiobjective Algorithm for Automatic Detection of Oil Spill Spreading from Full Polarimetric SAR Data
Published in Maged Marghany, Automatic Detection Algorithms of Oil Spill in Radar Images, 2019
The quantum machine learning is based on the Grover algorithm, which is based on constructing a coherent quantum system. In this view, m presents the pattern and it is known as the pattern-sorting process. Let us assume a set D = {ψ(P)} of polarimetric SAR features which has m patterns of the oil spill and look-alike features as a training set, the aim is to produce | ψ〉 such that () |ψ(P)〉=∑m∈Pψ(P)|P〉
Teamplay
Published in Volker Knecht, AI for Physics, 2023
In any case, quantum computing may enhance ML applications not only in terms of speed but can lead to entirely new algorithms (denoted as quantum machine learning).24,25
The unified effect of data encoding, ansatz expressibility and entanglement on the trainability of HQNNs
Published in International Journal of Parallel, Emergent and Distributed Systems, 2023
Muhammad Kashif, Saif Al-Kuwari
In a hybrid design space context, variational quantum algorithms (VQAs) are the most popular class of algorithms. These algorithms utilize NISQ devices for evaluating the objective function through parameterized quantum circuits (PQCs) and classical devices for function optimization with respect to the target application. The VQAs have been studied for a wide range of applications, including quantum chemistry [7], state diagonalization [8], factorization [9], quantum optimization [10], and quantum field theory simulation [11,12]. Furthermore, these algorithms have also been studied in the context of noise resilience [13], trainability [14–16] and computational complexity [17,18]. In other words, VQAs closely resemble machine learning (ML) algorithms as they also train a computer to learn patterns [19]. Therefore, VQAs have been proposed as a quantum analog of various ML algorithms [10,20–24]. Consequently, the new field of quantum machine learning (QML) has emerged by merging quantum computation and ML.
Brain Tumour Classification Using Quantum Support Vector Machine Learning Algorithm
Published in IETE Journal of Research, 2023
Tarun Kumar, Dilip Kumar, Gurmohan Singh
QML lies at the intersection of ML and quantum computing. [8]. The data processing in quantum machine learning is done on quantum computers. Quantum algorithms are generally derived from classical algorithms so that they can be used on quantum computers. The methods like deep neural networks in classical machine learning can identify the statistical patterns present in data and are capable of producing data of the same patterns [9,10]. It is observed that if information processed in quantum systems/algorithms produces statistical patterns which classical computers find hard to produce, then surely quantum algorithms can identify the patterns which classical computers failed to identify easily [9]. QML algorithms utilize both unsupervised and supervised learning techniques. In quantum algorithms, data are mapped in qubits followed by unitary operations on them and finally deliver the output upon measuring the state of qubits [23].
Modelling agricultural drought: a review of latest advances in big data technologies
Published in Geomatics, Natural Hazards and Risk, 2022
Ismaguil Hanadé Houmma, Loubna El Mansouri, Sébastien Gadal, Maman Garba, Rachid Hadria
Unlike traditional methods based on spatial interpolation of in-situ measurements or multivariate statistical modelling of drought, the joint use of multi-sensor remote sensing and machine learning models now offers the possibility of better understanding the spatio-temporal complexity of the drought phenomenon. Along with the explosion of multi-sensor and multispectral data, the use of machine learning algorithms now covers all aspects of multivariate drought modeling. Information taken on several biophysical variables that control vegetation growth and stress conditions can be generated at multiple temporal and spatial resolutions. The use of artificial intelligence techniques in the fusion of data from several satellites, in improving spatial resolution, or in estimating the relative contributions of drought-related covariates has given new direction to methods and approaches to descriptive modelling of agricultural drought. Both machine learning and deep learning models have been widely used to describe and/or to simulate several aspects of agricultural drought. Similarly, the use of hybrid and reinforcement learning models is an emerging trend in the field of drought modelling. On the other hand, at the current state of knowledge, quantum machine learning models have not yet been tested in multivariate drought modeling (Garcíaa et al. 2022). However, these new algorithms have shown the ability to simulate the complex phenomenon that evolves over time. In the fields of quantitative finance, in particular the predictive modeling of market uncertainties, quantum machine learning has been of great interest. Due to the complex, stochastic and highly evolving nature of drought, the applicability of such approaches should be tested. Analysis of the recent literature highlights several composite models developed in several regions of the world to identify the multidimensional and multifactorial nature of agricultural drought. A large part of these studies combines, the use of multi-sensor remote sensing, artificial intelligence techniques and to some extent the use of cloud computing platforms (Wu et al. 2015; Park et al. 2016; Samantaray et al. 2019; Sun et al. 2017; An et al. 2019; Shen et al. 2019; Son et al. 2021; Khan and Gilani 2021; Schwartz et al. 2022).