flâneur — a map of the web's best reading

Calculus on Computational Graphs: Backpropagation -- colah's blog

colah.github.io · 2,225 words · saved by 4 readers

Backpropagation is the key algorithm that makes training deep models computationally tractable. For modern neural networks, it can make training with gradient descent as much as ten million times faster, relative to a naive implementation. That’s the difference between a model taking a week to train and taking 200,000 years.

Calculus on Computational Graphs: Backpropagation -- colah's blog Calculus on Computational Graphs: Backpropagation Posted on August 31, 2015 Introduction Backpropagation is the key algorithm that makes training deep models computationally tractable. For modern neural networks, it can make training with gradient descent as much as ten million times faster, relative to a naive implementation. That’s the difference between a model taking a week to train and taking 200,000 years. Beyond its use in deep learning, backpropagation is a powerful computational tool in many other areas, ranging from we

Explore this link on the map →

saved by

related reading