首页|Researchers from Trinity College Dublin Detail New Studies and Findings in the Area of Networks [Shallow Quantum Neural Networks (Sqnns) With Application To Crack Identification]
Researchers from Trinity College Dublin Detail New Studies and Findings in the Area of Networks [Shallow Quantum Neural Networks (Sqnns) With Application To Crack Identification]
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Network Daily News - Investigatorspublish new report on Networks. According to news originating from Dublin, Ireland, by NewsRx correspondents,research stated, “Quantum neural networks have been explored in a number of tasks includingimage recognition. Most of the approaches involve using quantum gates in the neurons.”Our news journalists obtained a quote from the research from Trinity College Dublin, “Hybrid neuralnetworks combining classical and quantum layers are recently being studied. The goal of the hybridizationis to exploit the generalization benefits of quantum networks while reducing the requisite number of qubits.In this context, a Shallow Quantum Neural Network (SQNN) is proposed in this paper. Such architectureshave not been studied previously on image processing tasks. The SQNN is expected to be successful inimage classification tasks with limited training set size. Two types of SQNNs have been developed, these areResNet-SQNNs and VGG16-SQNNs. The SQNN models are applied to the problem of detection of surfacecracks on images. Introduction of hybrid classical-quantum layers in a typical pretrained neural networkmodel detects cracks with a greater validation accuracy as compared to classical Res-NNs and VGG16-NNs.Moreover, an entangled feature mapping has been incorporated with the parameterized quantum circuit inSQNNs. This outperforms classical approaches providing improved accuracy and training times.”
DublinIrelandEuropeNetworksNeural NetworksTrinity College Dublin
NETL
NSTL
