Classification of the MNIST data set with quantum slow feature analysis

Kerenidis, Iordanis; Luongo, Alessandro

doi:10.1103/physreva.101.062327

Cited by 35 publications

(30 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparable results are different such that making comparisons does not necessarily make complete sense, however for the sake of completeness and a gauge of the quality of our system we include comparisons with other systems with descriptions on how they differ. One paper discusses using kNN and PCA to classify MNIST, and with comparable PCA dimensions attains an accuracy of around 35% [32]. Comparing our systems performance to Tensorflow Quantum (TF-Q), we are able to attain 12.51% better results when distinguishing 0's and 1's, and 11.7% better results when distinguishing between numbers 3 and 8.…”

Section: Binary Classification Of the Mnist Datasetmentioning

confidence: 85%

Quantum Computing Aided Machine Learning Through Quantum State Fidelity

Stein¹

2021

Preprint

View full text Add to dashboard Cite

Tremendous progress has been witnessed in artificial intelligence within the domain of neural network backed deep learning systems and its applications. As we approach the post Moore’s Law era, the limit of semiconductor fabrication technology along with a rapid increase in data generation rates have lead to an impending growing challenge of tackling newer and more modern machine learning problems. In parallel, quantum computing has exhibited rapid development in recent years. Due to the potential of a quantum speedup, quantum based learning applications have become an area of significant interest, in hopes that we can leverage quantum systems to solve classical problems. In this work, we propose a quantum deep learning architecture; we demonstrate our quantum neural network architecture on tasks ranging from binary and multi-class classification to generative modelling. Powered by a modified quantum differentiation function along with a hybrid quantum-classic design, our architecture encodes the data with a reduced number of qubits and generates a quantum circuit, loading it onto a quantum platform where the model learns the optimal states iteratively. We conduct intensive experiments on both the local computing environment and IBM-Q quantum platform. The evaluation results demonstrate that our architecture is able to outperform Tensorflow-Quantum by up to 12.51% and 11.71% for a comparable classic deep neural network on the task of classification trained with the same network settings. Furthermore, our GAN architecture runs the discriminator and the generator purely on quantum hardware and utilizes the swap test on qubits to calculate the values of loss functions. In comparing our quantum GAN, we note our architecture is able to achieve similar performance with 98.5% reduction on the parameter set when compared to classical GANs. With the same number of parameters, additionally, QuGAN outperforms other quantum based GANs in the literature for up to 125.0% in terms of similarity between generated distributions and original data sets.

show abstract

Section: Binary Classification Of the Mnist Datasetmentioning

confidence: 85%

Quantum Computing Aided Machine Learning Through Quantum State Fidelity

Stein¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…SVMs could still be used to calculate prediction probabilities for such a multi-class classification problem [31]. Since the task of classification itself is still an active area of research with connections to many other scientific fields (such as quantum mechanics [26] with promising results [2,13]), it can be expected that the quality and performance of classification methods is subject to future improvements.…”

Section: Discussionmentioning

confidence: 99%

Optimized data exploration applied to the simulation of a chemical process

Heese

Walczak

Seidel

et al. 2019

Computers & Chemical Engineering

View full text Add to dashboard Cite

In complex simulation environments, certain parameter space regions may result in non-convergent or unphysical outcomes. All parameters can therefore be labeled with a binary class describing whether or not they lead to valid results. In general, it can be very difficult to determine feasible parameter regions, especially without previous knowledge. We propose a novel algorithm to explore such an unknown parameter space and improve its feasibility classification in an iterative way. Moreover, we include an additional optimization target in the algorithm to guide the exploration towards regions of interest and to improve the classification therein. In our method we make use of well-established concepts from the field of machine learning like kernel support vector machines and kernel ridge regression. From a comparison with a Kriging-based exploration approach based on recently published results we can show the advantages of our algorithm in a binary feasibility classification scenario with a discrete feasibility constraint violation. In this context, we also propose an improvement of the Kriging-based exploration approach. We apply our novel method to a fully realistic, industrially relevant chemical process simulation to demonstrate its practical usability and find a comparably good approximation of the data space topology from relatively few data points.

show abstract

“…Quantum Machine Learning techniques are currently impaired by NISQ devices limitations [24]. Thus, many proposed QML applications rely on using wellknown datasets, where pre-processing techniques are standard [16,25,26].…”

Section: Methodsmentioning

confidence: 99%

Dementia Prediction Applying Variational Quantum Classifier

Sierra-Sosa,

Arcila-Moreno,

Garcia-Zapirain

et al. 2020

Preprint

View full text Add to dashboard Cite

Dementia is the fifth cause of death worldwide with 10 million new cases every year. Healthcare applications using machine learning techniques have almost reached the physical limits while more data is becoming available resulting from the increasing rate of diagnosis. Recent research in Quantum Machine Learning (QML) techniques have found different approaches that may be useful to accelerate the training process of existing machine learning models and provide an alternative to learn more complex patterns. This work aims to report a real-world application of a Quantum Machine Learning Algorithm, in particular, we found that using the implemented version for Variational Quantum Classification (VQC) in IBM's framework Qiskit allows predicting dementia in elderly patients, this approach proves to provide more consistent results when compared with a classical Support Vector Machine (SVM) with a linear kernel using different number of features.

show abstract

Classification of the MNIST data set with quantum slow feature analysis

Cited by 35 publications

References 31 publications

Quantum Computing Aided Machine Learning Through Quantum State Fidelity

Quantum Computing Aided Machine Learning Through Quantum State Fidelity

Optimized data exploration applied to the simulation of a chemical process

Dementia Prediction Applying Variational Quantum Classifier

Contact Info

Product

Resources

About