2005 Special issue: Recursive principal components analysis

Authors:
Thomas Voegtlin
Affiliations:
INRIA-Campus Scientifique, B.P. 239 F-54506 Vandoeuvre-Les-Nancy Cedex, France
Venue:
Neural Networks - Special issue on neural networks and kernel methods for structured domains
Year:
2005

Citing 11
Cited 2

Neural networks and principal component analysis: learning from examples without local minima

Neural Networks
Recursive distributed representations

Artificial Intelligence - On connectionist symbol processing
Original Contribution: Associative memory with nonmonotone dynamics

Neural Networks
Computability with low-dimensional dynamical systems

Theoretical Computer Science
On the computational power of neural nets

Journal of Computer and System Sciences
Dynamical recognizers: real time language recognition by analog computers

Theoretical Computer Science
Real-time computing without stable states: a new framework for neural computation based on perturbations

Neural Computation
Linear recursive distributed representations

Neural Networks
Long Short-Term Memory

Neural Computation
A learning algorithm for continually running fully recurrent neural networks

Neural Computation
Learning long-term dependencies with gradient descent is difficult

IEEE Transactions on Neural Networks

Evolving hypernetwork models of binary time series for forecasting price movements on stock markets

CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Exact solutions for recursive principal components analysis of sequences and trees

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

A recurrent linear network can be trained with Oja's constrained Hebbian learning rule. As a result, the network learns to represent the temporal context associated to its input sequence. The operation performed by the network is a generalization of Principal Components Analysis (PCA) to time-series, called Recursive PCA. The representations learned by the network are adapted to the temporal statistics of the input. Moreover, sequences stored in the network may be retrieved explicitly, in the reverse order of presentation, thus providing a straight-forward neural implementation of a logical stack.