Choosing the right framework in Agentic AI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the popular machine learning framework.

Agentic AI

import [1] as ml

Drag options to blanks, or click blank then click option'

Atensorflow

Bpandas

Cmatplotlib

Dnumpy

Attempts:

3 left

💡 Hint

Common Mistakes

Using pandas which is for data manipulation, not ML framework.

Using matplotlib which is for plotting, not ML framework.

TensorFlow is a popular framework for machine learning and AI tasks.

2fill in blank

medium

Complete the code to create a simple neural network layer using the framework.

Agentic AI

model = ml.keras.Sequential([ml.keras.layers.Dense([1], activation='relu')])

Drag options to blanks, or click blank then click option'

Aoptimizer

Binput_shape

C64

Dloss

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'input_shape' which is a parameter but not the neuron count.

Using 'optimizer' or 'loss' which are unrelated here.

The number 64 specifies the number of neurons in the Dense layer.

3fill in blank

hard

Fix the error in the code to compile the model with an optimizer.

Agentic AI

model.compile(optimizer=[1], loss='sparse_categorical_crossentropy')

Drag options to blanks, or click blank then click option'

A'relu'

B'adam'

C'accuracy'

Dadam

Attempts:

3 left

💡 Hint

Common Mistakes

Not using quotes around the optimizer name causes errors.

Using 'accuracy' or 'relu' as optimizer which are incorrect.

The optimizer name must be a string, so it needs quotes.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that filters features with importance above 0.1.

Agentic AI

important_features = {k: v for k, v in feature_importances.items() if v [1] [2]

Drag options to blanks, or click blank then click option'

A>

B0.1

C<

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>' reverses the filter logic.

Using 1 as threshold filters out too many features.

The code keeps features with importance greater than 0.1.

5fill in blank

hard

Fill all three blanks to create a training loop that runs for 5 epochs and prints loss each epoch.

Agentic AI

for epoch in range([1]):
    history = model.fit(X_train, y_train, epochs=1, verbose=0)
    print(f"Epoch { [2] }: Loss = {{history.history['[3]'][0]}}")

Drag options to blanks, or click blank then click option'

A10

Bepoch + 1

Closs

D5

Attempts:

3 left

💡 Hint

Common Mistakes

Using 10 epochs instead of 5.

Printing epoch without adding 1 starts from 0.

Using 'accuracy' instead of 'loss' in history key.

The loop runs 5 times, printing the loss after each epoch with epoch number starting at 1.