Journal ArticleDOI
Learning representations by back-propagating errors
Reads0
Chats0
TLDR
Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.Abstract:
We describe a new learning procedure, back-propagation, for networks of neurone-like units. The procedure repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector. As a result of the weight adjustments, internal ‘hidden’ units which are not part of the input or output come to represent important features of the task domain, and the regularities in the task are captured by the interactions of these units. The ability to create useful new features distinguishes back-propagation from earlier, simpler methods such as the perceptron-convergence procedure1.read more
Citations
More filters
Journal ArticleDOI
Generalized information potential criterion for adaptive system training
Deniz Erdogmus,Jose C. Principe +1 more
TL;DR: A generalization of the error entropy criterion that enables the use of any order of Renyi's entropy and any suitable kernel function in density estimation is proposed and shown that the proposed entropy estimator preserves the global minimum of actual entropy.
Journal ArticleDOI
A comparison of statistical approaches for modelling fish species distributions
TL;DR: In this article, a comparison of traditional and alternative techniques for predicting species distributions using logistic regression analysis, linear discriminant analysis, classification trees and artificial neural networks to model: (1) the presence of 27 fish species as a function of habitat conditions in 286 temperate lakes located in south-central Ontario, Canada and (2) simulated data sets exhibiting deterministic, linear and non-linear species response curves.
Journal ArticleDOI
Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN)
TL;DR: An image-processing technique for rib suppression by means of a multiresolution massive training artificial neural network (MTANN) would be potentially useful for radiologists as well as for CAD schemes in detection of lung nodules on chest radiographs.
Book
Handbook of fish biology and fisheries
Paul J. B. Hart,John D. Reynolds +1 more
TL;DR: The Human Dimension of Fisheries Science: (P. J. Reynolds, N. Dulvy And C. Roberts) uncovers the human dimension of fisheries science as well as the science and management of fisheries, and some of the aspects of management and ecology that have changed over time.
Proceedings ArticleDOI
Deep neural networks for anatomical brain segmentation
TL;DR: In this paper, a deep artificial neural network (ANN) is used to segment the human brain into anatomical regions based on 3D and orthogonal 2D intensity patches and distances to the regional centroids.