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
Bayesian Methods for Adaptive Models
John Bridle,Peter Cheeseman,Sidney Fels,Steve Gull,Andreas V. M. Herz,John J. Hopfield,Doug Kerns,Allen Knutsen,David Koerner,Mike Lewicki,Tom Loredo,Steve Luttrell,Ronny Meir,Ken Miller,Marcus Mitchell,Radford M. Neal,Steve Nowlan,David Robinson,Ken Rose,Sibusiso Sibisi,John Skilling,Haim Sompolinsky +21 more
TL;DR: The Bayesian framework for model comparison and regularisation is demonstrated by studying interpolation and classification problems modelled with both linear and non–linear models and it is shown that the careful incorporation of error bar information into a classifier’s predictions yields improved performance.
Journal ArticleDOI
Monte Carlo convolution for learning on non-uniformly sampled point clouds
TL;DR: MCCNN as mentioned in this paper represents the convolution kernel itself as a multilayer perceptron, phrasing convolution as a Monte Carlo integration problem, using this notion to combine information from multiple samplings at different levels, and using Poisson disk sampling as a scalable means of hierarchical point cloud learning.
Journal ArticleDOI
Deep Learning for Acoustic Modeling in Parametric Speech Generation: A systematic review of existing techniques and future trends
Zhen-Hua Ling,Shiyin Kang,Heiga Zen,Andrew W. Senior,Mike Schuster,Xiaojun Qian,Helen Meng,Li Deng +7 more
TL;DR: In this article, Hidden Markov Models (HMMs) and Gaussian Mixture Models (GMMs) are used for generating low-level speech waveforms from high-level symbolic inputs via intermediate acoustic feature sequences.
Journal ArticleDOI
Monthly Rainfall Prediction Using Wavelet Neural Network Analysis
TL;DR: In this paper, an attempt has been made to find an alternative method for rainfall prediction by combining the wavelet technique with Artificial Neural Network (ANN), which has been applied to monthly rainfall data of Darjeeling rain gauge station.
Journal ArticleDOI
An intelligent-agent-based fuzzy group decision making model for financial multicriteria decision support: The case of credit scoring
TL;DR: A novel intelligent-agent-based fuzzy group decision making (GDM) model is proposed as an effective multicriteria decision analysis (MCDA) tool for credit risk evaluation.