Related Experiment Video
Updated: Apr 30, 2026

Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
Simple and fast calculation of the second-order gradients for globalized dual heuristic dynamic programming in neural
Abstract:
We derive an algorithm to exactly calculate the mixed second-order derivatives of a neural network's output with respect to its input vector and weight vector. This is necessary for the adaptive dynamic programming (ADP) algorithms globalized dual heuristic programming (GDHP) and value-gradient learning. The algorithm calculates the inner product of this second-order matrix with a given fixed vector in a time that is linear in the number of weights in the neural network. We use a "forward accumulation" of the derivative calculations which produces a much more elegant and easy-to-implement solution than has previously been published for this task. In doing so, the algorithm makes GDHP simple to implement and efficient, bridging the gap between the widely used DHP and GDHP ADP methods.
Related Concept Videos
Implicit Differentiation: Problem Solving
Second Derivatives of Implicit Functions
Implicit Differentiation
Second Derivative Test: Problem Solving
Second Derivatives and Laplace Operator
Consider a scalar function. The curl of its...
Gradient and Del Operator