Results 1  10
of
1,284,375
Practical GradientDescent for Memristive Crossbars
"... Abstract — This paper discusses implementations of gradientdescent based learning algorithms on memristive crossbar arrays. The Unregulated Step Descent (USD) is described as a practical algorithm for feedforward online training of large crossbar arrays. It allows fast feedforward fully parallel ..."
Abstract
 Add to MetaCart
Abstract — This paper discusses implementations of gradientdescent based learning algorithms on memristive crossbar arrays. The Unregulated Step Descent (USD) is described as a practical algorithm for feedforward online training of large crossbar arrays. It allows fast feedforward fully
parameters such as cr and A, that is Pr(lw , or) = Pr(). Posterior probabilities of network weights are as follows. For regression with Gaussian error and unknown a,
"... This paper has covered Bayesian theory relevant to the problem of training feedforward connectionist networks. We now sketch out how this might be put together in practice, assuming a standard gradient descent algorithm as used during search ..."
Abstract
 Add to MetaCart
This paper has covered Bayesian theory relevant to the problem of training feedforward connectionist networks. We now sketch out how this might be put together in practice, assuming a standard gradient descent algorithm as used during search
A General FeedForward Algorithm for Gradient Descent in Connectionist Networks
, 1990
"... An extended feedforward algorithm for recurrent connectionist networks is presented. This algorithm, which works locally in time, is derived both for discreteintime networks and for continuous networks. Several standard gradient descent algorithms for connectionist networks (e.g. [48], [30], [28] ..."
Abstract

Cited by 5 (3 self)
 Add to MetaCart
An extended feedforward algorithm for recurrent connectionist networks is presented. This algorithm, which works locally in time, is derived both for discreteintime networks and for continuous networks. Several standard gradient descent algorithms for connectionist networks (e.g. [48], [30], [28
Learning LongTerm Dependencies with Gradient Descent is Difficult
 TO APPEAR IN THE SPECIAL ISSUE ON RECURRENT NETWORKS OF THE IEEE TRANSACTIONS ON NEURAL NETWORKS
"... Recurrent neural networks can be used to map input sequences to output sequences, such as for recognition, production or prediction problems. However, practical difficulties have been reported in training recurrent neural networks to perform tasks in which the temporal contingencies present in th ..."
Abstract

Cited by 375 (35 self)
 Add to MetaCart
in the input/output sequences span long intervals. We showwhy gradient based learning algorithms face an increasingly difficult problem as the duration of the dependencies to be captured increases. These results expose a tradeoff between efficient learning by gradient descent and latching on information
Improving LongTerm Online Prediction with Decoupled Extended Kalman Filters
, 2002
"... Long shortterm memory (LSTM) recurrent neural networks (RNNs) outperform traditional RNNs when dealing with sequences involving not only shortterm but also longterm dependencies. The decoupled extended Kalman filter learning algorithm (DEKF) works well in online environments and reduces significa ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
significantly the number of training steps when compared to the standard gradientdescent algorithms.
A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm
 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS
, 1993
"... A new learning algorithm for multilayer feedforward networks, RPROP, is proposed. To overcome the inherent disadvantages of pure gradientdescent, RPROP performs a local adaptation of the weightupdates according to the behaviour of the errorfunction. In substantial difference to other adaptive tech ..."
Abstract

Cited by 924 (34 self)
 Add to MetaCart
A new learning algorithm for multilayer feedforward networks, RPROP, is proposed. To overcome the inherent disadvantages of pure gradientdescent, RPROP performs a local adaptation of the weightupdates according to the behaviour of the errorfunction. In substantial difference to other adaptive
Algorithms for Nonnegative Matrix Factorization
 In NIPS
, 2001
"... Nonnegative matrix factorization (NMF) has previously been shown to be a useful decomposition for multivariate data. Two different multiplicative algorithms for NMF are analyzed. They differ only slightly in the multiplicative factor used in the update rules. One algorithm can be shown to minim ..."
Abstract

Cited by 1222 (5 self)
 Add to MetaCart
. The algorithms can also be interpreted as diagonally rescaled gradient descent, where the rescaling factor is optimally chosen to ensure convergence.
Greedy Function Approximation: A Gradient Boosting Machine
 Annals of Statistics
, 2000
"... Function approximation is viewed from the perspective of numerical optimization in function space, rather than parameter space. A connection is made between stagewise additive expansions and steepest{descent minimization. A general gradient{descent \boosting" paradigm is developed for additi ..."
Abstract

Cited by 962 (12 self)
 Add to MetaCart
Function approximation is viewed from the perspective of numerical optimization in function space, rather than parameter space. A connection is made between stagewise additive expansions and steepest{descent minimization. A general gradient{descent \boosting" paradigm is developed
Algorithmic mechanism design
 Games and Economic Behavior
, 1999
"... We consider algorithmic problems in a distributed setting where the participants cannot be assumed to follow the algorithm but rather their own selfinterest. As such participants, termed agents, are capable of manipulating the algorithm, the algorithm designer should ensure in advance that the agen ..."
Abstract

Cited by 656 (21 self)
 Add to MetaCart
that the agents ’ interests are best served by behaving correctly. Following notions from the field of mechanism design, we suggest a framework for studying such algorithms. Our main technical contribution concerns the study of a representative task scheduling problem for which the standard mechanism design tools
The algorithmic analysis of hybrid systems
 THEORETICAL COMPUTER SCIENCE
, 1995
"... We present a general framework for the formal specification and algorithmic analysis of hybrid systems. A hybrid system consists of a discrete program with an analog environment. We model hybrid systems as nite automata equipped with variables that evolve continuously with time according to dynamica ..."
Abstract

Cited by 771 (71 self)
 Add to MetaCart
We present a general framework for the formal specification and algorithmic analysis of hybrid systems. A hybrid system consists of a discrete program with an analog environment. We model hybrid systems as nite automata equipped with variables that evolve continuously with time according
Results 1  10
of
1,284,375