This paper reviews the novel concept of a controllable variational autoencoder (ControlVAE), discusses its parameter tuning to meet application needs, derives its key analytic properties, and offer…
Neural architecture search (NAS), which automatically designs the architectures of deep neural networks, has achieved breakthrough success over many applications in the past few years. Among differ…
In modern data science, dynamic tensor data prevail in numerous applications. An important task is to characterize the relationship between dynamic tensor datasets and external covariates. However,…
Polarization devices on lithium niobate thin film (LNTF) are vital components for photonic integrated circuits (PICs) on the novel platform. Because both linear and nonlinear devices on the anisotr…
We demonstrate a 1×8 binary tree optical beamforming network (OBFN) chip for a microwave photonic phased array antenna. The OBFN is formed by cascading multiple microring resonators (MRRs) working…
With the emergence of new services, the complex optical network environment makes it more difficult to predict network anomalies. This paper proposes a multi-index anomaly prediction scheme with hy…
We propose a method based on temporal ghost imaging (TGI) that enables signal transmission at an ultra-high frequency much higher than the bandwidth of the emitter in a visible light communication …
In this paper, we design a monolithic integrated micro-opto-electromechanical system(MOEMS) accelerometer based on the Michelson interferometer structure. The accelerometer realizes the on-chip int…
Reconstructing 3D human shape and pose from monocular images is challenging despite the promising results achieved by the most recent learning-based methods. The commonly occurred misalignment come…
Adversarial attacks on deep neural networks (DNNs) have been found for several years. However, the existing adversarial attacks have high success rates only when the information of the victim DNN i…