Researchers at Harvard University recently developed a quantum circuit-based algorithm inspired by convolutional neural networks (CNNs). This new technique is therefore called Quantum Convolutional Neural Network (QCNN).
The team found a connection between two characteristics of CNNS (multiple layers of quasi-local quantum gates and hierarchical processing of data) and two physics concepts known as locality and renormalization.
It appears that the resultant quantum circuit involves only log(n) number of parameters to be optimized for n-qubit input data, which is double exponential improvement compared to a standard approach, in which exp(n) number of parameters are optimized. (Phys.org)
