Title :
The effect of quantization on support vector machines with Gaussian kernel
Author :
Anguita, Davide ; Bozza, Giovanni
Author_Institution :
Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
Abstract :
We apply here a probabilistic method to predict the effect of quantizing the parameters of a support vector machine with Gaussian kernel. Thanks to the particular structure of the SVM, the dependency of the output from the quantization noise can be predicted with good accuracy, and a simple closed-form formula can be derived, without imposing any hard-to-verify assumption.
Keywords :
Gaussian processes; quantisation (signal); support vector machines; Gaussian kernel; probabilistic method; quantization noise; support vector machines; Accuracy; Embedded system; Hardware; Kernel; Neural networks; Performance analysis; Quantization; Registers; Silicon; Support vector machines;
Conference_Titel :
Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on
Print_ISBN :
0-7803-9048-2
DOI :
10.1109/IJCNN.2005.1555933