Computational meta-imagers synergize metamaterial hardware with advanced signal
processing approaches such as compressed sensing. Recent advances in artificial …

We consider the design of a single vector representation for an image that embeds and
aggregates a set of local patch descriptors such as SIFT. More specifically we aim to …

Three important properties of a classification machinery are i) the system preserves the core
information of the input data; ii) the training examples convey information about unseen …

A mechanism for compiling a generative description of an inference task into a neural
network. First, an arbitrary generative probabilistic model from the exponential family is …

A sparse and low-rank near-isometric linear embedding (SLRNILE) method has been
proposed to make dimensionality reduction and extract proper features for hyperspectral …

The problem of recovering a structured signal x∈ C p from a set of dimensionality-reduced
linear measurements b= Ax arises in a variety of applications, such as medical imaging …

Abstract A Generative Adversarial Network (GAN) with generator G trained to model the prior
of images has been shown to perform better than sparsity-based regularizers in ill-posed …

Linear encoding of sparse vectors is widely popular, but is commonly data-independent–
missing any possible extra (but a priori unknown) structure beyond sparsity. In this paper we …

A grand challenge in machine learning is the development of computational algorithms that
match or outperform humans in perceptual inference tasks that are complicated by nuisance …

The emergence of Internet of Things (IoT) applications and rapid advances in wireless
communication technologies have motivated a paradigm shift in the development of viable …