Dynamics of learning with restricted training sets

The dynamics of supervised learning in layered neural networks were studied in the regime where the size of the training set is proportional to the number of inputs. The evolution of macroscopic observables, including the two relevant performance measures can be predicted by using the dynamical replica theory. Three approximation schemes aimed at eliminating the need to solve a functional saddle-point equation at each time step have been derived.

Noise, regularizers, and unrealizable scenarios in online learning from restricted training sets

We study the dynamics of on-line learning in multilayer neural networks where training examples are sampled with repetition and where the number of examples scales with the number of network weights. The analysis is carried out using the dynamical replica method aimed at obtaining a closed set of coupled equations for a set of macroscopic variables from which both training and generalization errors can be calculated. We focus on scenarios whereby training examples are corrupted by additive Gaussian output noise and regularizers are introduced to improve the network performance. The dependence of the dynamics on the noise level, with and without regularizers, is examined, as well as that of the asymptotic values obtained for both training and generalization errors. We also demonstrate the ability of the method to approximate the learning dynamics in structurally unrealizable scenarios. The theoretical results show good agreement with those obtained by computer simulations.

Technology transfer to developing countries : the case of physical asset management in South Africa

This research investigates technology transfer (TT) to developing countries, with specific reference to South Africa. Particular attention is paid to physical asset management, which includes the maintenance of plant, equipment and facilities. The research is case based, comprising a main case study (the South African electricity utility, Eskom) and four mini-cases. A five level framework adapted from Salami and Reavill (1997) is used as the methodological basis for the formulation of the research questions. This deals with technology selection, and management issues including implementation and maintenance and evaluation and modifications. The findings suggest the Salami and Reavill (1997) framework is a useful guide for TT. The case organisations did not introduce technology for strategic advantage, but to achieve operational efficiencies through cost reduction, higher quality and the ability to meet customer demand. Acquirers favour standardised technologies with which they are familiar. Cost-benefit evaluations have limited use in technology acquisition decisions. Users rely on supplier expertise to compensate for poor education and technical training in South Africa. The impact of political and economic factors is more evident in Eskom than in the mini-cases. Physical asset management follows traditional preventive maintenance practices, with limited use of new maintenance management thinking. Few modifications of the technology or R&D innovations take place. Little use is made of explicit knowledge from computerised maintenance management systems. Low operating and maintenance skills are not conducive to the transfer of high-technology equipment. South African organisations acquire technology as items of plant, equipment and systems, but limited transfer of technology takes place. This suggests that operators and maintainers frequently do not understand the underlying technology, and like workers elsewhere, are not always inclined towards adopting technology in the workplace.