Abel Nyamapfene

  • Citations Per Year
Learn More
We present two separate algorithms for unsupervised multimodal processing. Our first proposal, the singlepass Hebbian linked self-organising map network, significantly reduces the training of Hebbian-linked selforganising maps by computing in a single epoch the weights of the links associating the separate modal maps. Our second proposal, based on the(More)
Pressure from industry, professional bodies and students for a reform to the curriculum and delivery style of engineering education has been mounting for a number of years. Although there have been many excellent individual initiatives, developments that span a whole school or faculty, encompassing a number of disciplines and departments are far rarer. This(More)
Current opinion suggests that language is a cognitive process in which different modalities such as perceptual entities, communicative intentions and speech are inextricably linked. As such, the process of child language acquisition is one in which the child learns to decipher this inextricability and to acquire language capabilities starting from(More)
We present a multimodal neural network model of child language acquisition at the one-word stage that is inspired by current views on brain processing which suggest that information in the brain is ultimately stored in a common amodal set of conceptual representations. Our model takes into account a child's perceived communicative intention and simulates(More)
We propose a gated multi-net system that simulates the transition of child language from the one-word stage to the two-word stage. In this system, a modified counterpropagation network simulates child language at the one-word stage, whilst an unsupervised temporal neural network simulates child language at the two-word stage. During simulation, inputs(More)
There is considerable anecdotal evidence that equine sports enthusiasts in Devon and Cornwall still shun equine event search websites in preference to traditional information sources such as newspapers, magazines and word of mouth. On this basis, we have carried out a usability analysis of key equine event search websites serving Devon and Cornwall. This(More)
This paper presents an unsupervised, multimodal, neural network model of early child language acquisition that takes into account the child’s communicative intentions as well as the multimodal nature of language. The model exhibits aspects of one-word child language such as generalisation to new and unforeseen utterances, a U-shaped learning trajectory and(More)