Transfer Learning for Human & AI

Many quantum (convolutional) circuit ansaetze are proposed forgrayscale images classification tasks with promising empirical results . But the intra-channel information that is useful for vision tasks is not extracted effectively . This is the first work of a quantum convolutional circuit to deal with RGB images with a higher test accuracy compared to the purely classical CNNs . We also investigate the relationship between the size of quantum circuit ansatzand the learnability of the hybrid quantum-classical neuralnetwork. We wedemonstrate that a larger size of the quantum circuit Ansatz improvespredictive performance in multiclass classification tasks, providing usefulinsights for near term quantum algorithm developments. Through experiments based on CIFAR-10 and MNIST datasets, we wedemonstrated that a bigger size of . the quantum circuits ansatz improves performance in .

Author(s) : Yu Jing, Yang Yang, Chonghang Wu, Wenbing Fu, Wei Hu, Xiaogang Li, Hua Xu

Links : PDF - Abstract

Code :


Keywords : quantum - circuit - tasks - convolutional - size -

• Bioinformatics Specialization on Coursera
• Data Science A-Z
• Siraj Raval
• Machine Learning Nanodegree
• Neural Networks from Scratch with Python by Sentdex
• Applied Data Science with Python
• Deep Learning Nanodegree
• Practical Deep Learning for Coders – Part 1