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
Improved Computation for Levenberg–Marquardt Training
Bogdan M. Wilamowski,Hao Yu +1 more
TL;DR: The improved computation presented in this paper is aimed to optimize the neural networks learning process using Levenberg-Marquardt (LM) algorithm, and the improved memory and time efficiencies are especially true for large sized patterns training.
Book
Graph Representation Learning
TL;DR: This work has shown that graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry, and building relational inductive biases into deep learnin...
Journal ArticleDOI
Advanced Spectral Classifiers for Hyperspectral Images: A review
TL;DR: The classification of hyperspectral images is a challenging task for a number of reasons, such as the presence of redundant features, the imbalance among the limited number of available training samples, and the high dimensionality of the data.
Journal ArticleDOI
Machine Learning of Molecular Electronic Properties in Chemical Compound Space
Grégoire Montavon,Matthias Rupp,Vivekanand V. Gobre,Álvaro Vázquez-Mayagoitia,Katja Hansen,Alexandre Tkatchenko,Alexandre Tkatchenko,Klaus-Robert Müller,Klaus-Robert Müller,O. Anatole von Lilienfeld +9 more
TL;DR: In this article, a deep multi-task artificial neural network is used to predict multiple electronic ground and excited-state properties, such as atomization energy, polarizability, frontier orbital eigenvalues, ionization potential, electron affinity and excitation energies.
Proceedings ArticleDOI
Lossy Image Compression with Compressive Autoencoders
TL;DR: In this article, the authors proposed a new approach to the problem of optimizing autoencoders for lossy image compression, and showed that minimal changes to the loss are sufficient to train deep autoencoder competitive with JPEG 2000 and outperforming recently proposed approaches based on RNNs.