ianchanning + deeplearning   38

Differentiable Image Parameterizations
A powerful, under-explored tool for neural network visualizations and art.
chrisolah  research  deeplearning  neuralnetworks  vgg  visualizations 
7 days ago by ianchanning
Differentiable Programming for Image Processing and Deep Learning in Halide
We extend the image processing language Halide with general reversemode automatic differentiation (AD), and the ability to automatically optimize the implementation of gradient computations. This enables automatic computation of the gradients of arbitrary Halide programs, at high performance, with little programmer effort. A key challenge is to structure the gradient code to retain parallelism. We define a simple algorithm to automatically schedule these pipelines, and show how Halide’s existing scheduling primitives can express and extend the key AD optimization of "checkpointing."
halide  differentiableprogramming  deeplearning  performance 
12 days ago by ianchanning
TVM Stack
End to End Deep Learning Compiler Stack for CPUs, GPUs and specialized accelerators
deeplearning  neuralnetworks  artificialintelligence 
12 days ago by ianchanning
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky, University of Toronto
Ilya Sutskever, University of Toronto
Geoffrey E. Hinton, University of Toronto
2012
neuralnetworks  deeplearning  research  papers  cnn  2012 
february 2018 by ianchanning

Copy this bookmark:



description:


tags: