Search Results for author: Andrew Lavin

Found 3 papers, 2 papers with code

On the Efficiency of Convolutional Neural Networks

no code implementations4 Apr 2024 Andrew Lavin

Deep learning researchers have used convnets to produce accurate results that were unachievable a decade ago.

Computational Efficiency

Fast Algorithms for Convolutional Neural Networks

5 code implementations CVPR 2016 Andrew Lavin, Scott Gray

The algorithms compute minimal complexity convolution over small tiles, which makes them fast with small filters and small batch sizes.

Pedestrian Detection Self-Driving Cars

maxDNN: An Efficient Convolution Kernel for Deep Learning with Maxwell GPUs

1 code implementation27 Jan 2015 Andrew Lavin

This paper describes maxDNN, a computationally efficient convolution kernel for deep learning with the NVIDIA Maxwell GPU.

Computational Efficiency

Cannot find the paper you are looking for? You can Submit a new open access paper.