Related papers: Exploring local fNL estimators based on the binned…
We present an upgraded combined estimator, based on Minkowski Functionals and Neural Networks, with excellent performance in detecting primordial non-Gaussianity in simulated maps that also contain a weighted mixture of Galactic…
This paper presents the concept of "model-based neural network"(MNN), which is inspired by the classic artificial neural network (ANN) but for different usages. Instead of being used as a data-driven classifier, a MNN serves as a modeling…
Recent image inpainting methods show promising results due to the power of deep learning, which can explore external information available from a large training dataset. However, many state-of-the-art inpainting networks are still limited…
This paper proposes a machine learning-assisted channel estimation approach for massive MIMO systems, leveraging DNNs to outperform traditional LS and MMSE methods. In 5G and beyond, accurate channel estimation mitigates pilot contamination…
In recent years, Spiking Neural Networks (SNNs) have demonstrated great successes in completing various Machine Learning tasks. We introduce a method for learning image features by \textit{locally connected layers} in SNNs using…
In this article, we propose a novel standalone hybrid Spiking-Convolutional Neural Network (SC-NN) model and test on using image inpainting tasks. Our approach uses the unique capabilities of SNNs, such as event-based computation and…
An improved estimator for the amplitude fnl of local-type non-Gaussianity from the cosmic microwave background (CMB) bispectrum is discussed. The standard estimator is constructed to be optimal in the zero-signal (i.e., Gaussian) limit.…
We introduce a scheme based on machine learning and deep neural networks to model the environmental dependence of the electronic polarizability in insulating materials. Application to liquid water shows that training the network with a…
An inverse method for parameters estimation of infinite cylinders (the dielectric properties, location, and radius) in two dimensions from amplitude-only microwave information is presented. To this end two different Artificial Neural…
We propose a local modelling approach using deep convolutional neural networks (CNNs) for fine-grained image classification. Recently, deep CNNs trained from large datasets have considerably improved the performance of object recognition.…
In recent years, the spectral analysis of appropriately defined kernel matrices has emerged as a principled way to extract the low-dimensional structure often prevalent in high-dimensional data. Here we provide an introduction to spectral…
For various applications, the relations between the dependent and independent variables are highly nonlinear. Consequently, for large scale complex problems, neural networks and regression trees are commonly preferred over linear models…
For the efficient execution of deep convolutional neural networks (CNN) on edge devices, various approaches have been presented which reduce the bit width of the network parameters down to 1 bit. Binarization of the first layer was always…
Additive models play an essential role in studying non-linear relationships. Despite many recent advances in estimation, there is a lack of methods and theories for inference in high-dimensional additive models, including confidence…
Binary Neural Networks (BNNs) rely on a real-valued auxiliary variable W to help binary training. However, pioneering binary works only use W to accumulate gradient updates during backward propagation, which can not fully exploit its power…
We measure the skewness power spectrum of the Cosmic Microwave Background (CMB) anisotropies optimized for a detection of the secondary bispectrum generated by the correlation of the CMB lensing potential with integrated Sachs-Wolfe effect…
We investigate a semiparametric regression model where one gets noisy non linear non invertible functions of the observations. We focus on the application to bearings-only tracking. We first investigate the least squares estimator and prove…
Learning with few labeled data is a key challenge for visual recognition, as deep neural networks tend to overfit using a few samples only. One of the Few-shot learning methods called metric learning addresses this challenge by first…
This paper presents a Bayesian sampling approach to bandwidth estimation for the local linear estimator of the regression function in a nonparametric regression model. In the Bayesian sampling approach, the error density is approximated by…
This paper proposes an improved training algorithm for binary neural networks in which both weights and activations are binary numbers. A key but fairly overlooked feature of the current state-of-the-art method of XNOR-Net is the use of…