Reset
Showing 20 of 413 academic articles

Spectrally-normalized margin bounds for neural networks

Peter L. Bartlett, Dylan J. Foster, Matus Telgarsky • arXiv (Cornell University) (2017)

This paper presents a margin-based multiclass generalization bound for neural networks that scales with their margin-normalized "spectral complexity": their Lipschitz constant, meaning the product of the spectral norms of the weight matrice...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1706.08498

Weight Uncertainty in Neural Networks

Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, Daan Wierstra • arXiv (Cornell University) (2015)

We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop. It regularises the weights by minimising a compression ...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1505.05424

Bayesian Nonparametric Federated Learning of Neural Networks

Mikhail Yurochkin, Mayank Agarwal, Ghosh, Soumya, Kristjan H. Greenewald et al. • arXiv (Cornell University) (2019)

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. We develop a Bayesian nonparametric framework for federated learning with neural networks. Each data...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1905.12022

Neural Networks and Computing

Tommy W. S. Chow, Siu‐Yeung Cho • Series in electrical and computer engineering (2007)

This book covers neural networks with special emphasis on advanced learning methodologies and applications. It includes practical issues of weight initializations, stalling of learning, and escape from a local minima, which have not been co...

OPENALEX DOI: https://doi.org/10.1142/p487

Memristor devices for neural networks

Hongsik Jeong, Luping Shi • Journal of Physics D Applied Physics (2018)

Abstract Neural network technologies have taken center stage owing to their powerful computing capability for supporting deep learning in artificial intelligence. However, conventional synaptic devices such as SRAM and DRAM are not satisfac...

OPENALEX cc-by DOI: https://doi.org/10.1088/1361-6463/aae223

Prediction Intervals for Artificial Neural Networks

J. T. Gene Hwang, Aidong Adam Ding • Journal of the American Statistical Association (1997)

The artificial neural network (ANN) is becoming a very popular model for engineering and scientific applications. Inspired by brain architecture, artificial neural networks represent a class of nonlinear models capable of learning from data...

OPENALEX DOI: https://doi.org/10.1080/01621459.1997.10474027

Nonlinear Flight Control Using Neural Networks

Byoung S. Kim, Anthony J. Calise • Journal of Guidance Control and Dynamics (1997)

The theoretical developmentofa direct adaptivetracking controlarchitectureusingneuralnetworks ispresented. Emphasis is placed on utilization of neural networks in a  ight control architecture based on feedback linearization of the aircraft...

OPENALEX DOI: https://doi.org/10.2514/2.4029

Learning and Evolution in Neural Networks

Stefano Nolfi, Domenico Parisi, Jeffrey L. Elman • Adaptive Behavior (1994)

This article describes simulations on populations of neural networks that both evolve at the population level and learn at the individual level. Unlike other simulations, the evolutionary task (finding food in the environment) and the learn...

OPENALEX DOI: https://doi.org/10.1177/105971239400300102

Tensorizing Neural Networks

Alexander Novikov, Dmitry Podoprikhin, Anton Osokin, Dmitry Vetrov • arXiv (Cornell University) (2015)

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...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1509.06569

Quantum neural network

M. V. Altaĭsky • arXiv (Cornell University) (2001)

It is suggested that a quantum neural network (QNN), a type of artificial neural network, can be built using the principles of quantum information processing. The input and output qubits in the QNN can be implemented by optical modes with d...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.quant-ph/0107012

Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations

Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El‐Yaniv et al. • arXiv (Cornell University) (2016)

We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing ...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1609.07061

Neuromodulation Effect According to Lesion Location After Dual-Mode Brain Stimulation in Patients with Subacute Stroke: A Preliminary Study

Minji Lee, Wanjoo Park, Eunhee Park, Soon-Jae Kweon et al. • Applied Sciences (2024)

Dual-mode non-invasive brain stimulation using repetitive transcranial magnetic stimulation and transcranial direct current stimulation is known to help neurorehabilitation in patients with stroke. However, this neuromodulation effect may v...

DOAJ Open Access (DOAJ) DOI: 10.3390/app14219636

Improved PageRank Algorithm Based on User Behavior and Topic Similarity in Microblog Environment

ZHU Haodong,DING Wenxue,YANG Lizhi,FENG Jiamei • Jisuanji gongcheng (2017)

Aiming at the theme drifting and the page weight splitting of traditional PageRank algorithm,an improved PageRank algorithm is proposed.In order to improve the user query efficiency and search quality,combined with the time feedback factor,...

DOAJ Open Access (DOAJ) DOI: 10.3969/j.issn.1000-3428.2017.05.029

Statistics and Truth

C Radhakrishna Rao • WORLD SCIENTIFIC eBooks (1997)

Uncertainty, randomness and creation of new knowledge taming of uncertainty - evolution of statistics principles and strategies of data analysis - cross examination of data principles and strategies of data analysis - weighted and clouded d...

OPENALEX DOI: https://doi.org/10.1142/3454

A Heuristic Home Electric Energy Management System Considering Renewable Energy Availability

Victor J. Gutierrez-Martinez, Carlos A. Moreno-Bautista, Jose M. Lozano-Garcia, Alejandro Pizano-Martinez et al. • Energies (2019)

This paper presents the development of a heuristic-based algorithm for a Home Electric Energy Management System (HEEMS). The novelty of the proposal resides in the fact that solutions of the Pareto front, minimizing both the energy consumpt...

DOAJ Open Access (DOAJ) DOI: 10.3390/en12040671

High-Performance Tuning for Model Predictive Control for a Renewable Energy Grid-Interface Converter With LCL Filter

Jefferson S. Costa, Angelo Lunardi, Alessio Iovine, Darlan Alexandria Fernandes et al. • IEEE Access (2025)

Model predictive control (MPC) has emerged as a highly regarded control strategy in power electronics for renewable energy applications. While it minimizes tracking errors and control effort, a significant challenge is the lack of systemati...

DOAJ Open Access (DOAJ) DOI: 10.1109/ACCESS.2025.3603336

Laser-induced porous graphene electrodes from polyketimine membranes for paracetamol sensing

Sabrine Baachaoui, Walid Mabrouk, Khaled Charradi, Bechir Slimi et al. • Royal Society Open Science (2023)

The development of cost-effective materials for fabricating electrodes is crucial for drug, pharmaceutical and environmental applications. This paper presents the synthesis and characterization of a novel polyketimine (PKI) membrane obtaine...

DOAJ Open Access (DOAJ) DOI: 10.1098/rsos.230294

Materials Science

D.R. Powis, T. Follerås, Sheila A. Merson, A.D. Wilson • Journal of Dental Research (1982)

A study has been made on improving the adhesion of a glass ionomer cement by the chemical treatment of dentin and enamel surfaces. The most effective surface conditioners were high molecular weight substances containing a multiplicity of fu...

OPENALEX DOI: https://doi.org/10.1177/00220345820610120801