- Full text PDF available (64)
This study empirically investigates variations of hill climbing algorithms for training artiicial neural networks on the 5-bit parity classiication task. The experiments compare the algorithms when they use diierent combinations of random number distributions, variations in the step size and changes of the neural net-works' initial weight distribution. A… (More)
Perceptual aliasing makes topological navigation a difficult task. In this paper we present a general approach for topological SLAM (simultaneous localisation and mapping) which does not require motion or odometry information but only a sequence of noisy measurements from visited places. We propose a particle filtering technique for topological SLAM which… (More)
A graph is triangulated if it has no chordless cycle with at least four vertices (8k 4; C k 6 6 G). These graphs have been generalized by R. Hayward with the weakly triangulated graphs (8k 5; C k ; C k 6 6 G). In this note we propose a new generalization of triangulated graphs. A graph G is slightly triangulated if it satisses the two following conditions :… (More)
The tracking of features in real-time video streams forms the integral part of many important applications in human-computer interaction and computer vision. Unfortunately tracking is a computationally intensive task, since the video information used by the tracker is usually prepared by applying a series of image processing filters. Thus it is difficult to… (More)
In this paper we introduce methods to build a SOM that can be used as an isometric map for mobile robots. That is, given a dataset of sensor readings collected at points uniformly distributed with respect to the ground, we wish to build a SOM whose neurons (prototype vectors in sensor space) correspond to points uniformly distributed on the ground. Manifold… (More)
In this paper we present a system for appearance-based topological mapping and localisation using vision data. The algorithms are designed for robots which are equipped with FPGA cameras. Such cameras do not provide the entire image to the robot but simple image features like colour histograms.
We extend results due to Z.Bll azsik et al. on graphs with no induced C 4 and 2K 2 to the self-complementary class of (P 5 ; P 5)-free graphs. Moreover, we obtain an O(! 2)-binding function for this last class of graphs, answering thus partially a question of A. Gyy arff as.
Kernel methods such as kernel principal component analysis and support vector machines have become powerful tools for pattern recognition and computer vision. Unfortunately the high computational cost of kernel methods is a limiting factor for real-time classification tasks when running on the CPU of a standard PC. Over the last few years, commodity… (More)