Developments of the generative topographic mapping

The generative topographic mapping (GTM) model was introduced by Bishop et al. (1998, Neural Comput. 10(1), 215-234) as a probabilistic re- formulation of the self-organizing map (SOM). It offers a number of advantages compared with the standard SOM, and has already been used in a variety of applications. In this paper we report on several extensions of the GTM, including an incremental version of the EM algorithm for estimating the model parameters, the use of local subspace models, extensions to mixed discrete and continuous data, semi-linear models which permit the use of high-dimensional manifolds whilst avoiding computational intractability, Bayesian inference applied to hyper-parameters, and an alternative framework for the GTM based on Gaussian processes. All of these developments directly exploit the probabilistic structure of the GTM, thereby allowing the underlying modelling assumptions to be made explicit. They also highlight the advantages of adopting a consistent probabilistic framework for the formulation of pattern recognition algorithms.

An examination of the determinants of entrepreneurship at the regional level:the case of East Midlands region

Despite the importance of new firms to the economy, determinants of start-ups have mainly been examined at a country level and discussion of regional entrepreneurial activity has received less attention. Since there are significant variations in entrepreneurship rates across and within countries, such an investigation at a regional level would help in gaining an in depth understanding of the impact of the individual level resource endowments and neighbourhood characteristics on an individual’s decision to engage in entrepreneurial activity. The main aim of the thesis is to explore various theories of entrepreneurship and develop integrated frameworks for examining the determinants of entrepreneurial activity at a neighbourhood level in the East Midlands region in England. The specific objectives of the thesis are to examine how the individual level resources and the neighbourhood characteristics: (i) combine to influence an individual to engage in the different stages of the entrepreneurial process, (ii) influence natives and migrants to engage in start up activity and (iii) influence women and men to become self-employed and ambitious entrepreneurs. In terms of the methodology, the empirical analysis is based on two databases combined: 2006 to 2009 GEM East Midlands region and the English Index of Multiple Deprivation dataset. Based on the critical review of the literature on entrepreneurship the thesis develop theoretical frameworks which led to formulate hypotheses related to the differentiated impact of both individual and neighbourhood level factors on the propensity of an individual to be involved in entrepreneurial activity. The findings indicate that the determinants of entrepreneurial activity vary with human, financial and the local environment factors affecting the entrepreneurial process. Finally, the thesis calls for caution when developing and applying generic and specific policy measures aimed at promoting entry into entrepreneurship.