In this dissertation, we research classification algorithms created by regularization schemes. The design of these algorithms and their error analysis are completely explained. These algorithms rely on convex risk minimization with Tikhonov regularization. They require an admissible convex loss function, a hypothesis
This report presents a new method for dynamics identification and implements the identified models for enhanced haptic display. The report also derives an adaptive virtual coupling design technique for increasing the control performance in haptic displays. Practical dynamics models are essential for
Since the introduction of support vector machines (SVMs), much work has been done to make these machines more efficient in classification. In our work, we incorporated the preconditioned conjugate gradient method (PCG) with an adaptive constraint reduction method developed in 2007 to improve the efficiency of training the SVM when using an Interior-Point Method.
In this work we compare the prediction performance of three optimized technical indicators with a Support Vector Machine Neural Network. For the indicator part we picked the common used indicators: Relative Strength Index, Moving AverageConvergence Divergence and Stochastic Oscillator. For the Support