In this thesis several possibilities are investigated for improving the performance of Liquid State Machines. A Liquid State Machine is a relatively new system that is a Machine Learning system, which is capable of coping with temporal dependencies. Basic Recurrent Neural Networks often have problems with this. One reason for this is that it takes a long time to train the Recurrent Neural Netwo...

This final project attempts to show the differences of machine learning and optimization. In particular while optimization is concerned with exact solutions machine learning is concerned with generalization abilities of learners. We present examples in the areas of classification and regression where this difference is easy to observe as well as theoretical reasons of why this two areas are dif...

Defining tool paths for multiaxis milling is a difficult task that requires knowledge about the process and the behavior of the machine tool. Because of the high risks of multiaxis movements within a real machine, the resulting paths are safe but normally sub-optimal. This article introduces a new method to obtain tool paths, which are free of collisions and optimal in consideration, the machin...

A method of multi-nomenclature production in terms technical and economic indicators was considered. An integrated design system that is able to assess the real relationship “partmachine-transport device-device-tool” proposed, arelationship between elements an automated machine tool examined. The structure system, proposed form a mixed graph, represented by sets described nonlinear equations, d...

On critical applications, particularly embedded systems, the performance tuning requires multiple passes. Salto (System for Assembly Language Transformation and Optimization) is a retargetable framework for developing all the spectrum of tools that are needed for performance tuning on low-level codes (assembly-languages) on uniprocessors. Salto enables the building of pro ling, tracing and opti...