Project 13: Adam Optimizer Step Demo
ML Engineer
Builds on these lessons
Current Task
Objective
An optimizer like Adam uses computed gradients to update variables — apply_gradients() is the low-level call .fit() performs internally every step.
Task: apply one Adam optimization step to a variable and print its updated value.
index.py
import tensorflow as tf
x = tf.Variable(10.0)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.1)
with tf.GradientTape() as tape:
loss = x ** 2
grads = tape.gradient(loss, [x])
optimizer.apply_gradients(zip(grads, [x]))
print(x.numpy())
* Hint: Correct characters turn green, incorrect ones turn red.
Live Preview
🖼️
Verify your code to see the preview