Abstract BERT-based ranking models are emerging for its superior natural language understanding ability. All word relations and representations in the concatenation of query document modeled self-attention matrix as latent knowledge. However, some knowledge has none or negative effect on relevance prediction between document. We model observable unobservable confounding factors a causal graph p...

Volumetric imaging of samples using fluorescence microscopy plays an important role in various fields including physical, medical and life sciences. Here we report a deep learning-based volumetric image inference framework that uses 2D images are sparsely captured by standard wide-field microscope at arbitrary axial positions within the sample volume. Through recurrent convolutional neural netw...

Through evolution, animals have acquired central nervous systems (CNSs), which are extremely efficient information processing devices that improve an animal’s adaptability to various environments. It has been proposed that the process of information maximization (infomax1), which maximizes the information transmission from the input to the output of a feedforward network, may provide an explana...

This paper presents a new two-layer recurrent neural network (RNN) for a power system stabilizer (PSS) design called the recurrent neural network power system stabilizer (RNNPSS). The RNNPSS consists of a recurrent neural network identifier (RNNI) that tracks and identifies the power generator and a recurrent neural network controller (RNNC) that supplies an adaptive signal to the governor and ...

Recurrent Neural Networks were invented a long time ago, and dozens of different architectures have been published. In this paper we generalize recurrent architectures to a state space model, and we also generalize the numbers the network can process to the complex domain. We show how to train the recurrent network in the complex valued case, and we present the theorems and procedures to make t...