🍀 Challenge: Define the Neural Network Architecture

In this challenge, you are required to define the neural network architecture, the loss function, and the optimiser for the FMNIST data classification.

We'll cover the following

Problem statement

In this challenge, your task is to define the:

  • Network architecture

    • The input layer should have 784 nodes.
    • The hidden layer should have 200 nodes with the LeakyReLU activation applied to the output. The gradient of the left half of the function should be 0.020.02. Note that you must normalize the network signals just before they enter the final layer.
    • The output layer should have 10 nodes with the Sigmoid activation function applied to the output.
  • Loss function as BCE

  • Optimiser as Adam

Get hands-on with 1200+ tech skills courses.