自动微分 Automatic differentiation deep learning

• Automatic Differentiation in Deep/Machine Learning Platforms

• https://github.com/HIPS/autograd

• https://github.com/bshillingford/autobw.torch for torch.

• Automatic Differentiation, A.K.A please save me from backprop!

• Reverse-Mode Automatic Differentiation in Haskell Using the Accelerate Library

• Automatic differentiation in machine learning: a survey
  

• dl-frameworks.rst
  A comparison of Theano with other deep learning frameworks, highlighting a series of low-level design choices in no particular order.

• Automatic Differentiation (2009) _ Hacker News.pdf

• Automatic Differentiation and Neural Networks note8
  自动微分与神经网络note8

• Automatic Differentiation and Backpropagation CS701

• Automatic Differentiation of Algorithms for Machine Learning

• Can you give a visual explanation for the back propagation algorithm for neural networks?

Paste_Image.png

Paste_Image.png

• Artificial Intelligence Blog · Automatic Differentiation.pdf
  ustin Domke made a great blog post on automatic differentiation in 2009; andIntroduction to Automatic Differentiation and MATLAB Object-Oriented Programming is a very accessible paper on actually implementing autodiff in Matlab.
  Finally, www.autodiff.org/ seems to be the home of all things autodiff on the web.

• Calculus on Computational Graphs Backpropagation Hacker News.pdf

• Automatic Differentiation Or, mathemagically finding derivatives

• TensorFlow
  Auto-Differentiation
  Gradient based machine learning algorithms will benefit from TensorFlow's automatic differentiation capabilities. As a TensorFlow user, you define the computational architecture of your predictive model, combine that with your objective function, and just add data -- TensorFlow handles computing the derivatives for you. Computing the derivative of some values w.r.t. other values in the model just extends your graph, so you can always see exactly what's going on.