论文信息 - Using GPUs for machine learning algorithms

Using GPUs for machine learning algorithms

Using dedicated hardware to do machine learning typically ends up in disaster because of cost, obsolescence, and poor software. The popularization of graphic processing units (GPUs), which are now available on every PC, provides an attractive alternative. We propose a generic 2-layer fully connected neural network GPU implementation which yields over 3/spl times/ speedup for both training and testing with respect to a 3 GHz P4 CPU.

[1] M. Wand,et al. EXACT MEAN INTEGRATED SQUARED ERROR , 1992 .

[2] David G. Stork,et al. Pattern classification, 2nd Edition , 2000 .

[3] Shigeo Abe DrEng. Pattern Classification , 2001, Springer London.

[4] Patrice Y. Simard,et al. Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[5] Michael R. Macedonia,et al. The GPU Enters Computing's Mainstream , 2003, Computer.

[6] Pat Hanrahan,et al. Ray tracing on programmable graphics hardware , 2002, SIGGRAPH Courses.

[7] Christopher K. I. Williams,et al. Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning) , 2005 .

[8] Rüdiger Westermann,et al. Linear algebra operators for GPU implementation of numerical algorithms , 2003, SIGGRAPH Courses.

[9] P. Schröder,et al. Sparse matrix solvers on the GPU: conjugate gradients and multigrid , 2003, SIGGRAPH Courses.