flâneur — a map of the web's best reading

Backpropagation ≠ Chain Rule – Theory Dish

theorydish.blog · 785 words · saved by 1 readers

The chain rule is a fundamental result in calculus. Roughly speaking, it states that if a variable $latex c$ is a differentiable function of intermediate variables $latex b_1,\ldots,b_n$, and each …

The chain rule is a fundamental result in calculus. Roughly speaking, it states that if a variable is a differentiable function of intermediate variables , and each intermediate variable is itself a differentiable function of , then we can compute the derivative as follows: Besides being a handy tool for computing derivatives in calculus homework, the chain rule is closely related to the backpropagation algorithm that is widely-used for computing derivatives (gradients) in neural network training. This blog post by Boaz Barak is a beautiful tutorial on the chain rule and the backpropagation al

Explore this link on the map →

saved by

related reading