What is gradient check in PyBrain

Recipe Objective - What is gradient check in PyBrain?

We can numerically verify the gradients of the implementation of our neural network. PyBrain already includes a function that does just that, gradientCheck(). You can pass it to any network containing a structural component that you have programmed. It will check if the numeric gradients are (roughly) equal to the gradient specified by the _backwardImplementation() methods.

Complete Guide to Tensorflow for Deep Learning with Python for Free

For more related projects -

https://www.projectpro.io/projects/data-science-projects/deep-learning-projects
https://www.projectpro.io/projects/data-science-projects/tensorflow-projects

Let's try to implement gradient check on a network-

# Importing libraries
from pybrain.tools.shortcuts import buildNetwork
from pybrain.tests.helpers import gradientCheck
from pybrain.structure import TanhLayer

# Building a network with tanhlayer as hiddenclass
network = buildNetwork(2, 3, 1, hiddenclass=TanhLayer)

# Randomize the network
network.randomize()

# Checking the gradient
print(gradientCheck(network))


Output -
Perfect gradient
True

In this way, we can check the gradient of the network in the pybrain.

​