Self-organising neural networks for adaptive control

Self-organizing neural networks have been implemented in a wide range of application areas such as speech processing, image processing, optimization and robotics. Recent variations to the basic model proposed by the authors enable it to order state space using a subset of the input vector and to apply a local adaptation procedure that does not rely on a predefined test duration limit. Both these variations have been incorporated into a new feature map architecture that forms an integral part of an Hybrid Learning System (HLS) based on a genetic-based classifier system. Problems are represented within HLS as objects characterized by environmental features. Objects controlled by the system have preset targets set against a subset of their features. The system's objective is to achieve these targets by evolving a behavioural repertoire that efficiently explores and exploits the problem environment. Feature maps encode two types of knowledge within HLS — long-term memory traces of useful regularities within the environment and the classifier performance data calibrated against an object's feature states and targets. Self-organization of these networks constitutes non-genetic-based (experience-driven) learning within HLS. This paper presents a description of the HLS architecture and an analysis of the modified feature map implementing associative memory. Initial results are presented that demonstrate the behaviour of the system on a simple control task.

Using self-organising feature maps for the control of artificial organisms

Variations on the standard Kohonen feature map can enable an ordering of the map state space by using only a limited subset of the complete input vector. Also it is possible to employ merely a local adaptation procedure to order the map, rather than having to rely on global variables and objectives. Such variations have been included as part of a hybrid learning system (HLS) which has arisen out of a genetic-based classifier system. In the paper a description of the modified feature map is given, which constitutes the HLSs long term memory, and results in the control of a simple maze running task are presented, thereby demonstrating the value of goal related feedback within the overall network.

Modular non-computational-connectionist-hybrid neural network approach to robotic systems

Spiking neural networks are usually limited in their applications due to their complex mathematical models and the lack of intuitive learning algorithms. In this paper, a simpler, novel neural network derived from a leaky integrate and fire neuron model, the ‘cavalcade’ neuron, is presented. A simulation for the neural network has been developed and two basic learning algorithms implemented within the environment. These algorithms successfully learn some basic temporal and instantaneous problems. Inspiration for neural network structures from these experiments are then taken and applied to process sensor information so as to successfully control a mobile robot.

Passive and active hybrid approach to buildings design in Saudi Arabia

The building sector is one of the highest consumers of energy in the world. This has led to high dependency on using fossil fuel to supply energy without due consideration to its environmental impact. Saudi Arabia has been through rapid development accompanied by population growth, which in turn has increased the demand for construction. However, this fast development has been met without considering sustainable building design. General design practices rely on using international design approaches and features without considering the local climate and aspects of traditional passive design. This is by constructing buildings with a large amount of glass fully exposed to solar radiation. The aim of this paper is to investigate the development of sustainability in passive design and vernacular architecture. Furthermore, it compares them with current building in Saudi Arabia in terms of making the most of the climate. Moreover, it will explore the most sustainable renewable energy that can be used to reduce the environmental impact on modern building in Saudi Arabia. This will be carried out using case studies demonstrating the performance of vernacular design in Saudi Arabia and thus its benefits in terms of environmental, economic and social sustainability. It argues that the adoption of a hybrid approach can improve the energy efficiency as well as reduce the carbon footprint of buildings. This is by combining passive design, learning from the vernacular architecture and implementing innovative sustainable technologies.