Results 261 to 270 of about 2,008,811 (296)

Unsupervised Feature Learning Using Recurrent Neural Nets for Segmenting Hyperspectral Images

IEEE Geoscience and Remote Sensing Letters, 2021
Although deep learning is gaining more widespread use in hyperspectral image analysis, it is challenging to train high-capacity models in a supervised way--ground-truth sets are expensive to obtain, and they are practically always extremely imbalanced.
Lukasz Tulczyjew, Michal Kawulok, Jakub Nalepa   +2 more
openaire   +1 more source

Nonlinear predictive vector quantisation with recurrent neural nets

Neural Networks for Signal Processing III - Proceedings of the 1993 IEEE-SP Workshop, 2002
The nonlinear prediction capability of neural nets is applied to the design of improved predictive speech coders. Performance evaluations and comparisons with linear predictive speech coding are presented. These tests show the applicability of nonlinear prediction to speech coding and the improvement in coding performance. >
L. Wu, M. Niranjan, F. Fallside
openaire   +1 more source

Learning temporal sequences in recurrent self-organising neural nets

1997
The learning of temporal sequences is an extremely important component of human and animal behaviour. As well as the motor control involved in routine behaviour such as walking, running, talking, tool use and so on, humans have an apparently remarkable capacity for learning (and subsequently reproducing) temporal sequences. A new connectionist model of
Garry Briscoe, Terry Caelli
openaire   +2 more sources

Univariate Time Series Using Recurrent Neural Nets

2021
This chapter covers the basics of deep learning. First, it introduces the activation function, the loss function, and artificial neural network optimizers. Second, it discusses the sequence data problem and how a recurrent neural network (RNN) solves it. Third, the chapter presents a way of designing, developing, and testing the most popular RNN, which
openaire   +1 more source

A recurrent neural net approach to one-step ahead control problems

IEEE Transactions on Systems, Man, and Cybernetics, 1994
In this paper, we present a recurrent neural net technique to provide control actions for nonlinear dynamic systems. In most current neural net control approaches, two nets are usually required. One acts as a system emulator, and the other one is a controller network.
Percy P. C. Yip, Yoh-Han Pao
openaire   +2 more sources

Recurrent neural nets as dynamical Boolean systems with application to associative memory

IEEE Transactions on Neural Networks, 1997
Discrete-time/discrete-state recurrent neural networks are analyzed from a dynamical Boolean systems point of view in order to devise new analytic and design methods for the class of both single and multilayer recurrent artificial neural networks. With the proposed dynamical Boolean systems analysis, we are able to formulate necessary and sufficient ...
Paul Watta, Kaining Wang, Mohamad H. Hassoun   +2 more
openaire   +3 more sources

Prediction of software reliability using feedforward and recurrent neural nets

[Proceedings 1992] IJCNN International Joint Conference on Neural Networks, 2003
The authors present an adaptive modeling approach based on connectionist networks and demonstrate how both feedforward and recurrent networks and various training regimes can be applied to predict software reliability. They make an empirical comparison between this new approach and five well-known software reliability growth prediction models using ...
N. Karunanithi, D. Whitley
openaire   +1 more source

Schema generation in recurrent neural nets for intercepting a moving target

Biological Cybernetics, 2010
The grasping of a moving object requires the development of a motor strategy to anticipate the trajectory of the target and to compute an optimal course of interception. During the performance of perception-action cycles, a preprogrammed prototypical movement trajectory, a motor schema, may highly reduce the control load.
openaire   +2 more sources

Energy-Time Tradeoff in Recurrent Neural Nets

2015
In this chapter, we deal with the energy complexity of perceptron networks which has been inspired by the fact that the activity of neurons in the brain is quite sparse (with only about 1% of neurons firing). This complexity measure has recently been introduced for feedforward architectures (i.e., threshold circuits).
openaire   +2 more sources

A Myocardial T1-Mapping Framework with Recurrent and U-Net Convolutional Neural Networks

2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), 2020
Noise and aliasing artifacts arise in various accelerated cardiac magnetic resonance (CMR) imaging applications. In accelerated myocardial T1-mapping, the traditional three-parameter based nonlinear regression may not provide accurate estimates due to sensitivity to noise. A deep neural network-based framework is proposed to address this issue.
Haris Jeelani, Yang Yang 0110, Ruixi Zhou, Christopher M. Kramer, Michael Salerno, Daniel S. Weller   +5 more
openaire   +1 more source