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...
Abstract. We investigate the computational capabilities of probabilistic cellular automata by means of the density classification problem. We find that a specific probabilistic ...
Neural networks and other sophisticated machine learning algorithms frequently miss simple solutions that can be discovered by a more constrained learning methods. Transition from ...
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...
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...
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...
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]. ...
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...
Jindong Liu, David Perez-Gonzalez, Adrian Rees, Ha...