Evolutionary Neural Networks: Design Methodologies

By ai-depot | March 24, 2003

NN and genetic algorithms are both abstractions of natural processes, formulated into a computational model to harness the learning power and adaptive capabilities of both approaches. So called ‘adaptive learning’ demonstrates complex and purposeful behaviour thanks to the EA.

Written by Rinku Dewri.

Read the rest of this entry �

Tags: , , ,
Category: tutorial | No Comments »

Paradigmatic Considerations for an AI Interface for a Wearable Computer

By ai-depot | March 15, 2003

AI interfaces can be annoying. How should the information be presented to humans? Two concerns which must be adequately addressed by any designer of a wearable computer’s PC-based AI interface are distraction, and effect on human memory.

Written by Carol Stein.

Read the rest of this entry �

Tags: none
Category: essay | No Comments »

Getting Darwinian Evolution to Work

By ai-depot | February 12, 2003

Suggests that Darwinian evolution has higher levels of abstraction and that explicitly exploiting these in attempts to evolve software on computers could allow programs of greater sophistication. A multi-layered system is proposed which uses the concept of ‘evolving evolvability’.

Written by Paul Almond.

Read the rest of this entry �

Tags: none
Category: essay | No Comments »

Collective Intelligence in Social Insects

By ai-depot | January 20, 2003

Biological systems have long been a source of inspiration for AI. The latest paradigm to make the virtual leap comes from social insects - ant colonies and swarms. This article gives an overview of promising technologies to emerge from this field, looking at reasons ’swarm thinking’ might come to characterise the new millenium.

Written by David Gordon.

Read the rest of this entry �

Tags: none
Category: essay | No Comments »

Self-Organising Maps For Colour Recognition

By ai-depot | January 13, 2003

Looking into unsupervised learning techniques, this article offers a different approach to recognising colours. The system can train itself to match similar colours together. When asked about unknown colours, it learns them for future queries.

Written by Max Dennis Luesebrink.

Read the rest of this entry �

Tags: none
Category: tutorial | No Comments »

� Previous Entries Next Entries �