Academic Articles & Research Papers

Multilayer perceptron and neural networks

Abstract:- The attempts for solving linear inseparable problems have led to different variations on the number of layers of neurons and activation functions used. The backpropagation algorithm is the most known and used supervised learning ...

Lagrangian Neural Networks

Accurate models of the world are built upon notions of its underlying symmetries. In physics, these symmetries correspond to conservation laws, such as for energy and momentum. Yet even though neural network models see increasing use in the...

Cellular neural networks

A novel class of information-processing systems called cellular neural networks is proposed. Like neural networks, they are large-scale nonlinear circuits which process signals in real time. Like cellular automata, they are made of a massiv...

Cellular neural networks: applications

The theory of a novel class of information-processing systems, called cellular neural networks, which are capable of high-speed parallel signal processing, was presented in a previous paper (see ibid., vol.35, no.10, p.1257-72, 1988). A dyn...

Tensorizing Neural Networks

Deep neural networks currently demonstrate state-of-the-art performance in several domains. At the same time, models of this class are very demanding in terms of computational resources. In particular, a large amount of memory is required b...

Cellular neural networks: theory

A novel class of information-processing systems called cellular neural networks is proposed. Like neural networks, they are large-scale nonlinear analog circuits that process signals in real time. Like cellular automata, they consist of a m...

Discovering Physical Concepts with Neural Networks

Despite the success of neural networks at solving concrete physics problems, their use as a general-purpose tool for scientific discovery is still in its infancy. Here, we approach this problem by modeling a neural network architecture afte...

Understanding Neural Networks as Statistical Tools

Neural networks have received a great deal of attention over the last few years. They are being used in the areas of prediction and classification, areas where regression models and other related statistical techniques have traditionally be...

Neural networks for optimization and signal processing

From the Publisher: Artificial neural networks can be employed to solve a wide spectrum of problems in optimization, parallel computing, matrix algebra and signal processing. Taking a computational approach, this book explains how ANNs pro...

An Introduction to Convolutional Neural Networks

Abstract: The field of machine learning has taken a dramatic twist in re- cent times, with the rise of the Artificial Neural Network (ANN). These biologically inspired computational models can far exceed the per- performance of previous for...

cuDNN: Efficient Primitives for Deep Learning

We present a library of efficient implementations of deep learning primitives. Deep learning workloads are computationally intensive, and optimizing their kernels is difficult and time-consuming. As parallel architectures evolve, kernels mu...

Deep Learning for Instance Retrieval: A Survey

In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics. This abundance of content creation and sharing has introduced new challenges, par...

Artificial Intelligence

Artificial Intelligence (AI) refers to a set of technologies through which "intelligent machines are gaining the ability to learn, improve and make calculated decisions in ways that enable them to perform tasks previously thought to rely so...

Geoscientists’ Perspectives on Cyberinfrastructure Needs: A Collection of User Scenarios

Cyberinfrastructure (CI) is a standard tool in the geosciences, but the creation of successful CI remains difficult, and expensive projects can have significant consequences for scientific communities if they do not result in success. In th...

Evidence-based software engineering

Objective: Our objective is to describe how software engineering might benefit from an evidence-based approach and to identify the potential difficulties associated with the approach. Method: We compared the organisation and technical infra...

A QoS Routing Algorithm Based on Software-Defined Vehiclar Ad-Hoc Network

A Vehicular Ad-Hoc Network(VANET) is a Mobile Ad-Hoc Network(MANET) composed of mobile vehicular nodes.It does not rely on infrastructure to either establish a communication link orrealize communication. Owingto the high mobility of vehicle...

Nonlinear Dynamics of Swinging Clapper Bells under Arbitrary or Resonant Forcing Functions

Study of swinging clapper bells involves aspects encompassing sound and acoustic engineering, mechanical engineering, and structural engineering. From the musical point of view, clapper bells are directly played idiophone instruments, where...

A High-Resolution Rotational Analysis of 2‑Chloroethanol (HOCH(2)CH(2)Cl) and Its First Vibrationally Excited State.

Advances and perspectives for receiver function imaging of the Earth's internal discontinuities and velocity structures

Studying the structures, properties and origins of the Earth's internal discontinuities is an important part in the efforts to understand the physical and chemical properties of the layered Earth, as well as to explore the dynamic processes...

An IXPE-led X-Ray Spectropolarimetric Campaign on the Soft State of Cygnus X-1: X-Ray Polarimetric Evidence for Strong Gravitational Lensing

We present the first X-ray spectropolarimetric results for Cygnus X-1 in its soft state from a campaign of five IXPE observations conducted during 2023 May–June. Companion multiwavelength data during the campaign are likewise shown. The 2–8...