The study deals with issues of corporate management and pitfalls of the ''socialist supervision'' in Czechoslovak enterprises in the period of late socialism. Using documents of the Communist Party of Czechoslovakia and the State Security, period texts and specialized publications, it shows how party organs and state authorities were unsuccessfully trying to make supervisory mechanisms and audits a functional tool of the implementation of the ruling party´s economic policy. The author analyzes the supervisory and audit mechanisms that were used, and outlines basic reasons of the almost fatal failure of supervisory activities of the system which was, in a way, obsessed with supervision and control. He explains the systemic conditionality of the supervisory system which socialist managers often and in many respects bent to suit the needs of the enterprises they were in charge of; such situation naturally did not match the needs of the society as a whole. Using many specifi c cases as an example, the study graphically shows that members of the Czechoslovak corporate management community in the 1980s were fully aware of systemic, political and social limitations of the supervisory system which they managed to modify, fairly successfully, to suit intra-corporate conditions. The result was a situation in which the party leadership was reacting to increasingly obvious symptoms of the “agony of the centrally planned economy” by adopting various directives and guidelines to make the supervisory process more effective and to consistently promote the ''whoever manages - supervises'' principle. However, the anticipated effect did not materialize and, at the end of the day, the non-functional supervisory mechanisms made a substantial contribution to the collapse of the Communist regime in Czechoslovakia. and Překlad: Jiří Mareš
A boundary vector generator is a data barrier amplifier that improves the distribution model of the samples to increase the classification accuracy of the feed-forward neural network. It generates new forms of samples, one for amplifying the barrier of their class (fundamental multi-class outpost vectors) and the other for increasing the barrier of the nearest class (additional multi-class outpost vectors). However, these sets of boundary vectors are enormous. The reduced boundary vector generators proposed three boundary vector reduction techniques that scale down fundamental multi-class outpost vectors and additional multi-class outpost vectors. Nevertheless, these techniques do not consider the interval of the attributes, causing some attributes to suppress over the other attributes on the Euclidean distance calculation. The motivation of this study is to explore whether six normalization techniques; min-max, Z-score, mean and mean absolute deviation, median and median absolute deviation, modified hyperbolic tangent, and hyperbolic tangent estimator, can improve the classification performance of the boundary vector generator and the reduced boundary vector generators for maximizing class boundary. Each normalization technique pre-processes the original training set before the boundary vector generator or each of the three reduced boundary vector generators will begin. The experimental results on the real-world datasets generally confirmed that (1) the final training set having only FF-AA reduced boundary vectors can be integrated with one of the normalization techniques effectively when the accuracy and precision are prioritized, (2) the final training set having only the boundary vectors can be integrated with one of the normalization techniques effectively when the recall and F1-score are prioritized, (3) the Z-score normalization can generally improve the accuracy and precision of all types of training sets, (4) the modified hyperbolic tangent normalization can generally improve the recall of all types of training sets, (5) the min-max normalization can generally improve the accuracy and F1-score of all types of training sets, and (6) the selection of the normalization techniques and the training set types depends on the key performance measure for the dataset.