Generator vs Discriminator

Generative Adversarial Networks (GANs) consist of two neural networks competing against each other:

• Generator: Creates fake data samples aiming to mimic the real data distribution as closely as possible.
• Discriminator: Evaluates data samples and tries to distinguish between real and fake (generated) data.

The two networks are trained simultaneously in a zero-sum game, where the generator improves to produce more realistic samples and the discriminator improves to better detect fakes.

Example of a simple GAN architecture using TensorFlow/Keras:

import tensorflow as tf
from tensorflow.keras import layers

# Generator Model
def build_generator():
    model = tf.keras.Sequential([
        layers.Dense(128, activation='relu', input_shape=(100,)),
        layers.Dense(784, activation='sigmoid'),
        layers.Reshape((28, 28, 1))
    ])
    return model

# Discriminator Model
def build_discriminator():
    model = tf.keras.Sequential([
        layers.Flatten(input_shape=(28, 28, 1)),
        layers.Dense(128, activation='relu'),
        layers.Dense(1, activation='sigmoid')
    ])
    return model