Quantum Algorithms for Deep Convolutional Neural Networks

Abstract

Quantum computing is a new computational paradigm that promises applications in several fields, including machine learning. In the last decade, deep learning, and in particular Convolutional neural networks (CNN), have become essential for applications in signal processing and image recognition. Quantum deep learning, however remains a challenging problem, as it is difficult to implement non linearities with quantum unitaries. In this paper we propose a quantum algorithm for applying and training deep convolutional neural networks with a potential speedup. The quantum CNN (QCNN) is a shallow circuit, reproducing completely the classical CNN, by allowing non linearities and pooling operations. The QCNN is particularly interesting for deep networks and could allow new frontiers in image recognition, by using more or larger convolution kernels, larger or deeper inputs. We introduce a new quantum tomography algorithm with ${\ell }_{\infty }$ norm guarantees, and new applications of probabilistic sampling in the context of information processing. We also present numerical simulations for the classification of the MNIST dataset to provide practical evidence for the efficiency of the QCNN.

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
• The quest for a Quantum Neural Network

Cited by in corpus (17)

• Quantum convolutional neural network for classical data classification
• Hybrid Quantum-Classical Convolutional Neural Networks
• Quantum Methods for Neural Networks and Application to Medical Image Classification
• Quantum Spectral Clustering
• Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries
• Toward Trainability of Quantum Neural Networks
• Quantum Capsule Networks
• The Computational and Latency Advantage of Quantum Communication Networks
• Evaluating the Potential of Quantum Machine Learning in Cybersecurity: A Case-Study on PCA-based Intrusion Detection Systems
• Enabling Large-Scale and High-Precision Fluid Simulations on Near-Term Quantum Computers
• A hybrid quantum-classical framework for computational fluid dynamics
• Networked Quantum Services
• Data classification by quantum radial basis function networks
• Quantum Gram-Schmidt Processes and Their Application to Efficient State Read-out for Quantum Algorithms
• Quantum algorithms for SVD-based data representation and analysis
• Quantum Algorithm for Solving a Quadratic Nonlinear System of Equations
• Quantum algorithms for group convolution, cross-correlation, and equivariant transformations