Sciweavers

CONNECTION
2004
98views more  CONNECTION 2004»
13 years 6 months ago
Self-refreshing memory in artificial neural networks: learning temporal sequences without catastrophic forgetting
While humans forget gradually, highly distributed connectionist networks forget catastrophically: newly learned information often completely erases previously learned information. ...
Bernard Ans, Stephane Rousset, Robert M. French, S...
IJNSEC
2007
83views more  IJNSEC 2007»
13 years 6 months ago
Secure Logging for Irrefutable Administration
This paper presents a method that allows for securely saving a temporal sequence of data (log lines) in a file. Log lines are signed by an authority, and are thus unalterable wit...
Paolo Dal Checco, Francesco Bergadano, Davide Cava...
IEICET
2006
60views more  IEICET 2006»
13 years 6 months ago
Temporal Sequences of Patterns with an Inverse Function Delayed Neural Network
A network based on the Inverse Function Delayed (ID) model, which can recall a temporal sequence of patterns, is proposed. The classical problem, that the network is forced to make...
Johan Sveholm, Yoshihiro Hayakawa, Koji Nakajima
IJCAI
2003
13 years 7 months ago
Artificial Neural Network for Sequence Learning
This poster shows an artificial neural network capable of learning a temporal sequence. Directly inspired from a hippocampus model [Banquet et al, 1998], this architecture allows ...
Sorin Moga, Philippe Gaussier
ECCV
2010
Springer
13 years 9 months ago
Probabilistic Deformable Surface Tracking From Multiple Videos
Abstract. In this paper, we address the problem of tracking the temporal evolution of arbitrary shapes observed in multi-camera setups. This is motivated by the ever growing number...
AMDO
2006
Springer
13 years 10 months ago
Action Recognition Using Motion Primitives and Probabilistic Edit Distance
In this paper we describe a recognition approach based on the notion of primitives. As opposed to recognizing actions based on temporal trajectories or temporal volumes, primitive-...
Preben Fihl, Michael B. Holte, Thomas B. Moeslund,...
ICIAP
2003
ACM
14 years 6 months ago
Dense 3D interpretation of image sequences: a variational approach using anisotropic diffusion
The purpose of this study is to investigate a new method for recovering relative depth and 3D motion from a temporal sequence of monocular images. The method is direct insomuch as...
Hicham Sekkati, Amar Mitiche