Reset
Showing 20 of 2,274 academic articles

A survey of graphs in natural language processing

Vivi Năstase, Rada F. Mihalcea, Dragomir Radev • Natural Language Engineering (2015)

Abstract Graphs are a powerful representation formalism that can be applied to a variety of aspects related to language processing. We provide an overview of how Natural Language Processing problems have been projected into the graph framew...

OPENALEX Open Access DOI: https://doi.org/10.1017/s1351324915000340

Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

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

We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time. At training-time the binary weights and activations are used for computing the parameters gradients. During t...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1602.02830

Neural networks in control systems

Kumpati S. Narendra, Snehasis Mukhopadhyay • IEEE Conference on Decision and Control (CDC) (2005)

Some of the problems that arise in the control of nonlinear systems in the presence of uncertainty are considered. Multilayer neural networks and radial basis function networks are used in the design of identifiers and controllers, and grad...

OPENALEX DOI: https://doi.org/10.1109/cdc.1992.371803

Pattern Recognition with Neural Networks in C++

Abhijit S. Pandya, Robert B. Macy • CRC Press eBooks (2021)

From the Publisher: The addition of artificial neural network computing to traditionalpattern recognition has given rise to a new, different, and more powerful methodology that is presented in this interesting book. This is a practical gui...

OPENALEX DOI: https://doi.org/10.1201/9780138744274

A neural-network-based detection of epilepsy

Vivek Prakash Nigam, Daniel Graupe • Neurological Research (2004)

Diagnosis of epilepsy is primarily based on scalp-recorded electroencephalograms (EEG). Unfortunately the long-term recordings obtained from 'ambulatory recording systems' contain EEG data of up to one week duration, which has introduced ne...

OPENALEX DOI: https://doi.org/10.1179/016164104773026534

Heterogeneous Graph Neural Network

Chuxu Zhang, Dongjin Song, Chao Huang, Ananthram Swami et al. • ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (2019)

Representation learning in heterogeneous graphs aims to pursue a meaningful vector representation for each node so as to facilitate downstream applications such as link prediction, personalized recommendation, node classification, etc. This...

OPENALEX Open Access DOI: https://doi.org/10.1145/3292500.3330961

Multilayer perceptron and neural networks

Marius-Constantin Popescu, Valentina Emilia Bălaş, Liliana Perescu-Popescu, Nikos E. Mastorakis (2009)

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 ...

OPENALEX DOI: https://doi.org/10.5555/1639537.1639542

Self-Normalizing Neural Networks

Günter Klambauer, Thomas Unterthiner, Andreas Mayr, Sepp Hochreiter • arXiv (Cornell University) (2017)

Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks (FNN...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1706.02515

Lagrangian Neural Networks

Miles Cranmer, Sam Greydanus, Stephan Hoyer, Peter Battaglia et al. • arXiv (Cornell University) (2020)

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...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.2003.04630

The Graph Neural Network Model

Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner et al. • IEEE Transactions on Neural Networks (2008)

Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper,...

OPENALEX Open Access DOI: https://doi.org/10.1109/tnn.2008.2005605

Are artificial neural networks black boxes?

José M. Benítez, Juan Luis Castro, Ignacio Requena • IEEE Transactions on Neural Networks (1997)

Artificial neural networks are efficient computing models which have shown their strengths in solving hard problems in artificial intelligence. They have also been shown to be universal approximators. Notwithstanding, one of the major criti...

OPENALEX DOI: https://doi.org/10.1109/72.623216

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