papers
Publications (3)
cs.NE2015
maxDNN: An Efficient Convolution Kernel for Deep Learning with Maxwell GPUs
Andrew Lavin
This paper describes maxDNN, a computationally efficient convolution kernel for deep learning with the NVIDIA Maxwell GPU. maxDNN reaches 96.3% computational efficiency on typical…
cs.LG2024
On the Efficiency of Convolutional Neural Networks
Andrew Lavin
Since the breakthrough performance of AlexNet in 2012, convolutional neural networks (convnets) have grown into extremely powerful vision models. Deep learning researchers have use…
cs.NE2015
Fast Algorithms for Convolutional Neural Networks
Andrew Lavin, Scott Gray
Deep convolutional neural networks take GPU days of compute time to train on large data sets. Pedestrian detection for self driving cars requires very low latency. Image recognitio…