Quantum classification of the MNIST dataset with Slow Feature Analysis

Abstract

Quantum machine learning carries the promise to revolutionize information and communication technologies. While a number of quantum algorithms with potential exponential speedups have been proposed already, it is quite difficult to provide convincing evidence that quantum computers with quantum memories will be in fact useful to solve real-world problems. Our work makes considerable progress towards this goal. We design quantum techniques for Dimensionality Reduction and for Classification, and combine them to provide an efficient and high accuracy quantum classifier that we test on the MNIST dataset. More precisely, we propose a quantum version of Slow Feature Analysis (QSFA), a dimensionality reduction technique that maps the dataset in a lower dimensional space where we can apply a novel quantum classification procedure, the Quantum Frobenius Distance (QFD). We simulate the quantum classifier (including errors) and show that it can provide classification of the MNIST handwritten digit dataset, a widely used dataset for benchmarking classification algorithms, with $98.5\%$ accuracy, similar to the classical case. The running time of the quantum classifier is polylogarithmic in the dimension and number of data points. We also provide evidence that the other parameters on which the running time depends (condition number, Frobenius norm, error threshold, etc.) scale favorably in practice, thus ascertaining the efficiency of our algorithm.

arXiv commentAmeliorated details and plots

References in corpus (25)

• Scikit-learn: Machine Learning in Python
• Quantum algorithm for solving linear systems of equations
• Barren plateaus in quantum neural network training landscapes
• Quantum support vector machine for big data classification
• Quantum principal component analysis
• Parameterized quantum circuits as machine learning models
• Circuit-centric quantum classifiers
• Quantum Data Fitting
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• Implementing a distance-based classifier with a quantum interference circuit
• Unsupervised Machine Learning on a Hybrid Quantum Computer
• Quantum gradient descent for linear systems and least squares
• Hardware-efficient quantum random access memory with hybrid quantum acoustic systems
• Circuit-Based Quantum Random Access Memory for Classical Data
• Quantum machine learning for quantum anomaly detection
• Quantum-inspired algorithms in practice
• Quantum Discriminant Analysis for Dimensionality Reduction and Classification
• Quantum Neuron: an elementary building block for machine learning on quantum computers
• Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models
• Quantum Recommendation Systems
• A quantum algorithm to train neural networks using low-depth circuits
• Experimental realization of 105-qubit random access quantum memory
• Projective simulation with generalization
• Quantum computational finance: quantum algorithm for portfolio optimization
• Optimal Usage of Quantum Random Access Memory in Quantum Machine Learning

Cited by in corpus (26)

• Robust data encodings for quantum classifiers
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Mixed Quantum-Classical Method For Fraud Detection with Quantum Feature Selection
• q-means: A quantum algorithm for unsupervised machine learning
• Prospects and challenges of quantum finance
• Finding Angles for Quantum Signal Processing with Machine Precision
• Quantum algorithms for Second-Order Cone Programming and Support Vector Machines
• Quantum Dimensionality Reduction by Linear Discriminant Analysis
• Sublinear quantum algorithms for training linear and kernel-based classifiers
• How quantum computing can enhance biomarker discovery
• Evaluating the Potential of Quantum Machine Learning in Cybersecurity: A Case-Study on PCA-based Intrusion Detection Systems
• Optimized data exploration applied to the simulation of a chemical process
• QUILT: Effective Multi-Class Classification on Quantum Computers Using an Ensemble of Diverse Quantum Classifiers
• Recurrent Quantum Neural Networks
• Incremental Data-Uploading for Full-Quantum Classification
• Quantum Expectation-Maximization for Gaussian Mixture Models
• Quantum algorithms for SVD-based data representation and analysis
• Hybrid quantum-classical unsupervised data clustering based on the self-organizing feature map
• Quantum matching pursuit: A quantum algorithm for sparse representations
• Quantum Neural Networks in Practice: A Comparative Study with Classical Models from Standard Data Sets to Industrial Images
• Quantum-Inspired Classical Algorithm for Slow Feature Analysis
• Des-q: a quantum algorithm to provably speedup retraining of decision trees
• Typical Machine Learning Datasets as Low-Depth Quantum Circuits
• Quantum Algorithms for Unsupervised Machine Learning and Neural Networks
• Quantum Inspired Adaptive Boosting
• Quantum feature-map learning with reduced resource overhead