No abstract available. / Thesis (M.A.)-University of KwaZulu-Natal, Pietermaritzburg, 2009.

No abstract available. / Thesis (Ph.D)-University of Durban-Westville, 2002.

No abstract available. / Thesis (M.A.)-University of Natal, Durban, 2001.

No abstract available. / Thesis (Ph.D.)-University of Durban-Westville, 1990.

Thesis (MA)--Stellenbosch University, 1935. / Hand written copy, original hard-copy in J. S. Gericke Library Compact storage - KTES 362.292 FOU / No Abstract Available

The Baum-Welch algorithm for training hidden Markov models (HMMs) requires model topology and initial parameters to be specifed, and iteratively improves the model parameters. Sometimes prior knowledge of the process being modeled allows such specifcation, but often this knowledge is unavailable. Experimentation and guessing are resorted to. Techniques for discovering the model structure from observation data exist but their use is not commonplace. We propose a state split-ting approach to structure discovery, where states are split based on two heuristics: within-state autocorrelation and a measure of Markov violation in the state path. Statistical hypothesis testing is used to decide which states to split, providing a natural termination criterion and taking into account the number of observations assigned to each state, splitting states only when the data demands it. / Thesis (M.A.)-University of KwaZulu-Natal, Durban, 2009.

This paper is an analysis of aspects of Daniel Dennett's theory of human consciousness. For Dennett, the reasons why human consciousness is so unique among earthly creatures, and so manifestly powerful, are not to be found in the differences between our brains and those of other higher mammals, but rather in the ways in which the plasticity of our brains is harnessed by language and culture. According to Dennett, the best way to understand the enhancements and augmentations that result from enculturation is as a von Neumannesque virtual machine implemented in the parallel-distributed processing brain. This paper examines two questions that arise from the latter hypothesis: (1) If nonsymbolic, parallel-distributed networks accomplish all the representation and computation of the brain, what kind of explanation of the functionality of that brain, can legitimately maintain descriptions of procedures that are symbolic, serial, and real? (2) What kind of structural design, training, and resultant processing dynamics could enable a (human) brain to develop a competency for symbolic, serial procedures? Through addressing these questions, I argue that Dennett's theory of consciousness is broadly correct, investigate some other theorist's ideas that are highly compatible with Dennett's work, and consider some criticisms that have been levelled against it. / Thesis (M.A.)-University of Natal, Durban, 2003.

Thesis (MA) -- Stellenbosch University, 1949. / INLEIDING: Enige denker wat die geskiedenis van die filosofie bestudeer, gee daarmee te kenne dat die geskiedenis van die filosofie meer is as bloot 'n ry van aaneengeskakelde dog verwerpte sisteme. Die geskiedenis van die filosofie is nie 'n museum van historiese kuriositeite, wat vir die huidige denker van geen waar is nie. In die geskiedenis van die filosofie vind die denker die probleme terug waarmee hy homself ook besig hu alhoewel hierdie probleme steeds in 'n ander verband of vanuit 'n ander gesigspunt gestel is. Die geskiedenis van die filosofie is 'n leerskool vir elke denker. Die feit dat die geskiedenis van die filosofie 'n leerskool vir elke denker is, op wat ter punt van die geskiedenis hy ook staan, hou egter verskillende implikasies in.

Thesis(MA) -- Stellenbosch University, 1948. / No abstract available

Thesis (PhD)--Stellenbosch University, 1982. / No abstract available