ICANN
2009
Springer
13 years 9 months ago
2009
Springer
We present a neural system that recognizes faces under strong variations in pose and illumination. The generalization is learnt completely on the basis of examples of a subset of p...
ICANN
2009
Springer
13 years 9 months ago
2009
Springer
Abstract. We investigate the computational capabilities of probabilistic cellular automata by means of the density classification problem. We find that a specific probabilistic ...
ICANN
2009
Springer
13 years 9 months ago
2009
Springer
ICANN
2009
Springer
13 years 9 months ago
2009
Springer
ICANN
2009
Springer
13 years 9 months ago
2009
Springer
Neural networks and other sophisticated machine learning algorithms frequently miss simple solutions that can be discovered by a more constrained learning methods. Transition from ...
ICANN
2009
Springer
13 years 9 months ago
2009
Springer
Abstract. Many applications of machine learning involve sparse highdimensional data, where the number of input features is (much) larger than the number of data samples, d n. Predi...
ICANN
2009
Springer
13 years 9 months ago
2009
Springer
This paper proposes a modelling of Support Vector Machine (SVM) learning to address the problem of learning with sloppy labels. In binary classification, learning with sloppy labe...
ICANN
2009
Springer
13 years 9 months ago
2009
Springer
Learning to solve small instances of a problem should help in solving large instances. Unfortunately, most neural network architectures do not exhibit this form of scalability. Our...
ICANN
2009
Springer
13 years 9 months ago
2009
Springer
It has been known for some time that the synapses of the CA1 pyramidal cells are surprisingly unreliable at signalling the arrival of single spikes to the postsynaptic neuron [2]. ...
ICANN
2009
Springer
13 years 9 months ago
2009
Springer
This paper proposes a spiking neural network (SNN) of the mammalian auditory midbrain to achieve binaural multiple sound source localisation. The network is inspired by neurophysio...