Related papers: Studying Brazil-Nut Effect History Line using Disk…
The brain performs intelligent tasks with extremely low energy consumption. This work takes inspiration from two strategies used by the brain to achieve this energy efficiency: the absence of separation between computing and memory…
We compare the predictions of two different statistical mechanics approaches, corresponding to different physical measurements, proposed to describe binary granular mixtures subjected to some external driving (continuous shaking or tap…
The entrance to public universities in Brazil depends on scores obtained by students in Enem, Brazilian National Assessment of High School Education. This exam consists of four multiple choice tests (Language, Maths, Natural and Human…
Form-finding of unilateral membrane structures is commonly addressed by solving equilibrium equations with Finite Element Methods (FEMs). This paper investigates Physics-Informed Neural Networks (PINNs) as an alternative, where the…
The discovery of a minimum energy pathway (MEP) between metastable states is crucial for scientific tasks including catalyst and biomolecular design. However, the standard nudged elastic band (NEB) algorithm requires hundreds to tens of…
One of the most computationally intensive parts in modern recognition systems is an inference of deep neural networks that are used for image classification, segmentation, enhancement, and recognition. The growing popularity of edge…
This paper presents TULIP, a new architecture for a binary neural network (BNN) that uses an optimal schedule for executing the operations of an arbitrary BNN. It was constructed with the goal of maximizing energy efficiency per…
Recently, there have been some breakthroughs in graph analysis by applying the graph neural networks (GNNs) following a neighborhood aggregation scheme, which demonstrate outstanding performance in many tasks. However, we observe that the…
We propose an algorithm that uses energy mini- mization to estimate the current configuration of a non-rigid object. Our approach utilizes an RGBD image to calculate corresponding SURF features, depth, and boundary informa- tion. We do not…
The great success of Physics-Informed Neural Networks (PINN) in solving partial differential equations (PDEs) has significantly advanced our simulation and understanding of complex physical systems in science and engineering. However, many…
Graph representation learning has achieved great success in many areas, including e-commerce, chemistry, biology, etc. However, the fundamental problem of choosing the appropriate dimension of node embedding for a given graph still remains…
In this paper, we propose a Deep Active Ray Network (DARNet) for automatic building segmentation. Taking an image as input, it first exploits a deep convolutional neural network (CNN) as the backbone to predict energy maps, which are…
Agriculture is vital for global food security, but crops are vulnerable to diseases that impact yield and quality. While Convolutional Neural Networks (CNNs) accurately classify plant diseases using leaf images, their high computational…
Traditional network embedding primarily focuses on learning a continuous vector representation for each node, preserving network structure and/or node content information, such that off-the-shelf machine learning algorithms can be easily…
Context. Carbonaceous nano-grains play a fundamental role in the physico-chemistry of the interstellar medium (ISM) and especially of photon-dominated regions (PDRs). Their properties vary with the local physical conditions and affect the…
Recently, there has been growing interest in using physics-informed neural networks (PINNs) to solve differential equations. However, the preservation of structure, such as energy and stability, in a suitable manner has yet to be…
This document describes the conceptual design for the Offline Software and Computing for the Deep Underground Neutrino Experiment (DUNE). The goals of the experiment include 1) studying neutrino oscillations using a beam of neutrinos sent…
The success of neural networks in image classification has inspired various hardware implementations on embedded platforms such as Field Programmable Gate Arrays, embedded processors and Graphical Processing Units. These embedded platforms…
A fully connected neural network was trained to model the K-shell ionization cross sections based on two input features: the atomic number and the incoming electron overvoltage. The training utilized a recent, updated compilation of…
We consider the problem of network coding across three unicast sessions over a directed acyclic graph, when each session has min-cut one. Previous work by Das et al. adapted a precoding-based interference alignment technique, originally…