Neural Networks and TensorFlow - Deep Learning Series [Part 15]

This is the lesson in which we start actually writing code for the convolutional neural network that we're going to train on the MNIST dataset.

So, here we're gonna work on a couple of helper functions that will ease our way into building the convolutional net. What are these helper functions?

We're gonna have two functions weight_variable and bias_variable that will help us initialize the weights and bias. We're also gonna have two functions for quickly creating convolutional layers in the network and one to build pooling layers (max_pool).

Finally, we're gonna have a function that will help us build a fully connected layer, which we might also use for the last layer in the network, the output layer. Please watch the video for the complete lesson.

To stay in touch with me, follow @cristi

Cristi Vlad Self-Experimenter and Author