L1 and L2 regularization in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is L1 regularization in machine learning?

L1 regularization adds the sum of the absolute values of the model's weights to the loss. It helps make the model simpler by pushing some weights to zero, which can remove unimportant features.

beginner

What does L2 regularization do to a model's weights?

L2 regularization adds the sum of the squares of the model's weights to the loss. It encourages smaller weights overall but does not force them to zero, helping the model avoid overfitting.

intermediate

How do L1 and L2 regularization help prevent overfitting?

Both add a penalty to the loss based on the size of weights. This penalty discourages the model from fitting noise in the training data, making it generalize better to new data.

beginner

Show a simple TensorFlow code snippet to add L2 regularization to a Dense layer.

import tensorflow as tf
from tensorflow.keras import layers, regularizers

model = tf.keras.Sequential([
    layers.Dense(64, activation='relu', kernel_regularizer=regularizers.l2(0.01)),
    layers.Dense(1)
])

intermediate

What is the main difference in the effect of L1 vs L2 regularization on model weights?

L1 regularization can make some weights exactly zero, effectively selecting features. L2 regularization makes weights smaller but usually keeps them all nonzero.

Which regularization method can lead to sparse models by setting some weights to zero?

A Dropout

B L2 regularization

C L1 regularization

D Batch normalization

L1 regularization adds absolute value penalties that can push weights exactly to zero, creating sparsity.

What does L2 regularization add to the loss function?

A Sum of absolute weights

B Sum of weight inverses

C Sum of weights

D Sum of squared weights

L2 regularization adds the sum of the squares of the weights to the loss.

In TensorFlow, which argument adds L2 regularization to a Dense layer?

A bias_regularizer

B kernel_regularizer

C activity_regularizer

D dropout_rate

The kernel_regularizer argument applies regularization to the layer's weights.

Why do we use regularization in machine learning models?

A To prevent overfitting

B To reduce dataset size

C To speed up training

D To increase model complexity

Regularization helps prevent overfitting by penalizing large weights.

Which regularization method is more likely to keep all weights small but nonzero?

A L2 regularization

B Early stopping

C L1 regularization

D Data augmentation

L2 regularization shrinks weights but usually does not make them exactly zero.

Explain in your own words how L1 and L2 regularization help a model avoid overfitting.

Think about how adding extra cost to big weights changes the model.

Write a short TensorFlow code example showing how to add L1 regularization to a Dense layer.

Use tensorflow.keras.layers and regularizers.l1 with a small value.

Practice

1. What is the main purpose of using L1 and L2 regularization in TensorFlow models?

easy

A. To change the activation function of the model

B. To increase the size of the model weights

C. To prevent overfitting by adding penalties to large weights

D. To speed up the training process by skipping layers

Solution

1. Step 1: Understand the role of regularization

   L1 and L2 regularization add penalties to the loss function based on the size of the weights to reduce overfitting.

2. Step 2: Identify the effect on model weights

   These penalties discourage large weights, helping the model generalize better on new data.

3. Final Answer:

   To prevent overfitting by adding penalties to large weights -> Option C

4. Quick Check:

   Regularization = Prevent overfitting [OK]

Hint: Regularization adds penalty to weights to avoid overfitting [OK]

Common Mistakes:

• Thinking regularization speeds up training
• Confusing regularization with activation functions
• Believing regularization increases weight size

2. Which of the following is the correct way to add L2 regularization to a Dense layer in TensorFlow?

easy

A. Dense(64, kernel_regularizer=tf.keras.regularizers.l2(0.01))

B. Dense(64, regularizer=tf.keras.l2(0.01))

C. Dense(64, kernel_regularizer=tf.keras.regularizers.l1(0.01))

D. Dense(64, kernel_regularizer=tf.keras.regularizers.l1_l2(0.01))

Solution

1. Step 1: Recall the correct argument name

   The argument to add regularization in a Dense layer is kernel_regularizer.

2. Step 2: Use the correct regularizer function

   For L2 regularization, use tf.keras.regularizers.l2() with the penalty value.

3. Final Answer:

   Dense(64, kernel_regularizer=tf.keras.regularizers.l2(0.01)) -> Option A

4. Quick Check:

   Correct syntax = Dense(64, kernel_regularizer=tf.keras.regularizers.l2(0.01)) [OK]

Hint: Use kernel_regularizer with tf.keras.regularizers.l2 for L2 [OK]

Common Mistakes:

• Using 'regularizer' instead of 'kernel_regularizer'
• Using L1 regularizer when L2 is needed
• Wrong function call like tf.keras.l2 instead of tf.keras.regularizers.l2

3. What will be the effect on the weights after training a model with L1 regularization compared to no regularization?

medium

A. Weights will be larger to fit the training data better

B. Weights will not change compared to no regularization

C. Weights will be small but rarely zero

D. Weights will be exactly zero for some features, creating sparsity

Solution

1. Step 1: Understand L1 regularization effect

   L1 regularization adds absolute value penalties, encouraging some weights to become zero.

2. Step 2: Compare with no regularization

   Without regularization, weights can be large and non-sparse; L1 creates sparsity by zeroing some weights.

3. Final Answer:

   Weights will be exactly zero for some features, creating sparsity -> Option D

4. Quick Check:

   L1 = Sparsity with zero weights [OK]

Hint: L1 makes some weights zero, creating sparse models [OK]

Common Mistakes:

• Confusing L1 with L2 effects
• Thinking weights get larger with regularization
• Assuming weights remain unchanged

4. You wrote this code to add L2 regularization but get an error:

model.add(Dense(32, kernel_regularizer=tf.keras.regularizers.l2))

What is the error and how to fix it?

medium

A. Missing parentheses after l2; fix with l2(0.01)

B. kernel_regularizer should be regularizer

C. Dense layer does not support regularization

D. l2 should be replaced with l1

Solution

1. Step 1: Identify the error in regularizer usage

   The code uses tf.keras.regularizers.l2 without calling it as a function.

2. Step 2: Correct the syntax by adding parentheses and penalty value

   Use tf.keras.regularizers.l2(0.01) to create the regularizer instance.

3. Final Answer:

   Missing parentheses after l2; fix with l2(0.01) -> Option A

4. Quick Check:

   Call l2() with penalty value [OK]

Hint: Always call l1 or l2 with parentheses and penalty [OK]

Common Mistakes:

• Forgetting parentheses after l1 or l2
• Using 'regularizer' instead of 'kernel_regularizer'
• Thinking Dense layer can't have regularization

5. You want to build a TensorFlow model that uses both L1 and L2 regularization on the kernel weights of a Dense layer with penalties 0.001 and 0.01 respectively. Which code snippet correctly applies this?

hard

A. Dense(128, kernel_regularizer=tf.keras.regularizers.l2(0.01), kernel_regularizer=tf.keras.regularizers.l1(0.001))

B. Dense(128, kernel_regularizer=tf.keras.regularizers.l1_l2(l1=0.001, l2=0.01))

C. Dense(128, kernel_regularizer=tf.keras.regularizers.l1(0.001), bias_regularizer=tf.keras.regularizers.l2(0.01))

D. Dense(128, kernel_regularizer=tf.keras.regularizers.l1(0.001) + tf.keras.regularizers.l2(0.01))

Solution

1. Step 1: Understand how to combine L1 and L2 regularization

   TensorFlow provides l1_l2 regularizer to apply both penalties together on the same weights.

2. Step 2: Check the correct syntax for l1_l2

   Use tf.keras.regularizers.l1_l2(l1=0.001, l2=0.01) as the kernel_regularizer argument.

3. Final Answer:

   Dense(128, kernel_regularizer=tf.keras.regularizers.l1_l2(l1=0.001, l2=0.01)) -> Option B

4. Quick Check:

   Use l1_l2() for combined regularization [OK]

Hint: Use l1_l2() to combine L1 and L2 penalties [OK]

Common Mistakes:

• Trying to add two kernel_regularizer arguments
• Adding regularizers instead of using l1_l2
• Applying L1 to kernel and L2 to bias instead