In this paper, we present a gradient-free approach for training multi-layered neural networks based upon quantum perceptrons.
Combining symbolic human knowledge with neural networks provides a rule-based ante-hoc explanation of the output.
Again, it is unknown how to incorporate the expert prior knowledge about the global optimum into Bayesian optimization process.
This paper introduces a novel method to simultaneously super-resolve and colour-predict images acquired by snapshot mosaic sensors.
This paper introduces a newly collected and novel dataset (StereoMSI) for example-based single and colour-guided spectral image super-resolution.
We prove that the light field is a 2D series, thus, a specifically designed CNN-LSTM network is proposed to capture the continuity property of the EPI.
Moreover, the non-linearity in deep nets, often achieved by a rectifier unit, is here cast as a convolution in the frequency domain.