Quantum machine learning
≈ 8 min read
Names in other languages
No names in other languages are held for this entry yet.
Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.
Quantum machine learning (QML) is the study of quantum algorithms for machine learning. It often refers to quantum algorithms for machine learning tasks which analyze classical data, sometimes called quantum-enhanced machine learning. QML algorithms use qubits and quantum operations to try to improve the space and time complexity of classical machine learning algorithms. Hybrid QML methods involve both classical and quantum processing, where computationally difficult subroutines are outsourced to a quantum device.
These routines can be more complex in nature and executed faster on a quantum computer. Furthermore, quantum algorithms can be used to analyze quantum states instead of classical data. The term "quantum machine learning" is sometimes used to refer classical machine learning methods applied to data generated from quantum experiments (i.e. machine learning of quantum systems), such as learning the phase transitions of a quantum system or creating new quantum experiments.
QML also extends to a branch of research that explores methodological and structural similarities between certain physical systems and learning systems, in particular neural networks. For example, some mathematical and numerical techniques from quantum physics are applicable to classical deep learning and vice versa.…
Quantum machine learning (QML) is the study of quantum algorithms for machine learning. It often refers to quantum algorithms for machine learning tasks which analyze classical data, sometimes called quantum-enhanced machine learning. QML algorithms use qubits and quantum operations to try to improve the space and time complexity of classical machine learning algorithms. Hybrid QML methods involve both classical and quantum processing, where computationally difficult subroutines are outsourced to a quantum device.
These routines can be more complex in nature and executed faster on a quantum computer. Furthermore, quantum algorithms can be used to analyze quantum states instead of classical data. The term "quantum machine learning" is sometimes used to refer classical machine learning methods applied to data generated from quantum experiments (i.e. machine learning of quantum systems), such as learning the phase transitions of a quantum system or creating new quantum experiments.
QML also extends to a branch of research that explores methodological and structural similarities between certain physical systems and learning systems, in particular neural networks. For example, some mathematical and numerical techniques from quantum physics are applicable to classical deep learning and vice versa. Furthermore, researchers investigate more abstract notions of learning theory with respect to quantum information, sometimes referred to as "quantum learning theory".
Quantum convolution neural network (QCNN)
A novel design for multi-dimensional vectors that uses circuits as convolution filters is QCNN. It was inspired by the advantages of CNNs and the power of QML. It is made using a combination of a variational quantum circuit (VQC) and a deep neural network (DNN), fully utilizing the power of extremely parallel processing on a superposition of a quantum state with a finite number of qubits.
The main strategy is to carry out an iterative optimization process in the NISQ devices, without the negative impact of noise, which is possibly incorporated into the circuit parameter, and without the need for quantum error correction. The quantum circuit must effectively handle spatial information in order for QCNN to function as CNN. The convolution filter is the most basic technique for making use of spatial information.
One or more quantum convolutional filters make up a quantum convolutional neural network (QCNN), and each of these filters transforms input data using a quantum circuit that can be created in an organized or randomized way. Three parts that make up the quantum convolutional filter are: the encoder, the parameterized quantum circuit (PQC), and the measurement. The quantum convolutional filter can be seen as an extension of the filter in the traditional CNN because it was designed with trainable parameters.
Quantum neural networks take advantage of the hierarchical structures, and for each subsequent layer, the number of qubits from the preceding layer is decreased by a factor of two. For n input qubits, these structures have O(log(n)) layers, allowing for shallow circuit depth. Additionally, they are able to avoid "barren plateau," one of the most significant issues with PQC-based algorithms, ensuring trainability.
Despite the fact that the QCNN model does not include the corresponding quantum operation, the fundamental idea of the pooling layer is also offered to assure validity. In QCNN architecture, the pooling layer is typically placed between succeeding convolutional layers. Its function is to shrink the representation's spatial size while preserving crucial features, which allows it to reduce the number of parameters, streamline network computing, and manage over-fitting.
Such a process can be accomplished applying full Tomography on the state to reduce it all the way down to one qubit and then processed it. The most frequently used unit type in the pooling layer is max pooling, although there are other types as well. Similar to conventional feed-forward neural networks, the last module is a fully connected layer with full connections to all activations in the preceding layer.
Translational invariance, which requires identical blocks of parameterized quantum gates within a layer, is a distinctive feature of the QCNN architecture. A natural model of passive learning is Valiant's probably approximately correct (PAC) learning. Here the learner receives random examples (x,c(x)), where x is distributed according to some unknown distribution D. The learner's goal is to output a hypothesis function h such that h(x)=c(x) with high probability when x is drawn according to D.
The learner has to be able to produce such an 'approximately correct' h for every D and every target concept c in its concept class. We can consider replacing the random examples by potentially more powerful quantum examples \sum_x \sqrt{D(x)}|x,c(x)\rangle . In the PAC model (and the related agnostic model), this doesn't significantly reduce the number of examples needed: for every concept class, classical and quantum sample complexity are the same up to constant factors.
However, for learning under some fixed distribution D, quantum examples can be very helpful, for example for learning DNF under the uniform distribution. When considering time complexity, there exist concept classes that can be PAC-learned efficiently by quantum learners, even from classical examples, but not by classical learners (again, under plausible complexity-theoretic assumptions).
This passive learning type is also the most common scheme in supervised learning: a learning algorithm typically takes the training examples fixed, without the ability to query the label of unlabelled examples. Outputting a hypothesis h is a step of induction. Classically, an inductive model splits into a training and an application phase: the model parameters are estimated in the training phase, and the learned model is applied an arbitrary many times in the application phase.
In the asymptotic limit of the number of applications, this splitting of phases is also present with quantum resources.
Skepticism
While machine learning itself is now not only a research field but an economically significant and fast growing industry and quantum computing is a well established field of both theoretical and experimental research, QML remains a theoretical field of studies. Further, another obstacle exists at the prediction stage because the outputs of quantum learning models are inherently random. This creates an often considerable overhead, as many executions of a quantum learning model have to be aggregated to obtain an actual prediction.
Many of the leading scientists that extensively publish in the field of QML warn about the extensive hype around the topic and are very restrained if asked about its practical uses in the foreseeable future. Sophia Chen collected in 2020 some of the statements made by well known scientists in the field: "I think we haven't done our homework yet. This is an extremely new scientific field" - physicist Maria Schuld of Canada-based quantum computing startup Xanadu.
"When mixing machine learning with 'quantum,' you catalyse a hype-condensate." - Jacob Biamonte a contributor to the theory of quantum computation. "There is a lot more work that needs to be done before claiming quantum machine learning will actually work" - computer scientist Iordanis Kerenidis, the head of quantum algorithms at the Silicon Valley-based quantum computing startup QC Ware.
"I have not seen a single piece of evidence that there exists a meaningful [machine learning] task for which it would make sense to use a quantum computer and not a classical computer" - physicist Ryan Sweke of the Free University of Berlin in Germany.
Text derived from https://en.wikipedia.org/w/index.php?oldid=1375368884 under CC BY-SA 4.0; modifications have been made.