L1 and L2 regularization in TensorFlow - ML Experiment: Train & Evaluate

Experiment - L1 and L2 regularization

Problem:You have a neural network model trained on a dataset to classify images. The model achieves 98% accuracy on training data but only 75% on validation data.

Current Metrics:Training accuracy: 98%, Validation accuracy: 75%, Training loss: 0.05, Validation loss: 0.65

Issue:The model is overfitting: it performs very well on training data but poorly on validation data.

Your Task

Reduce overfitting by applying L1 and L2 regularization to the model layers to improve validation accuracy to at least 85% while keeping training accuracy below 92%.

You can only add L1 and L2 regularization to the Dense layers.

Do not change the model architecture or dataset.

Keep the number of epochs and batch size the same.

Hint 1

Hint 2

Hint 3

Solution

TensorFlow

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

# Load example dataset
mnist = tf.keras.datasets.mnist
(X_train, y_train), (X_val, y_val) = mnist.load_data()

# Normalize data
X_train, X_val = X_train / 255.0, X_val / 255.0

# Flatten images
X_train = X_train.reshape(-1, 28*28)
X_val = X_val.reshape(-1, 28*28)

# Define model with L1 and L2 regularization
model = models.Sequential([
    layers.Dense(128, activation='relu', input_shape=(28*28,),
                 kernel_regularizer=regularizers.l1_l2(l1=0.001, l2=0.001)),
    layers.Dense(64, activation='relu',
                 kernel_regularizer=regularizers.l1_l2(l1=0.001, l2=0.001)),
    layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

history = model.fit(X_train, y_train, epochs=10, batch_size=32, validation_data=(X_val, y_val))

Added L1 and L2 regularization with small values (0.001) to the Dense layers.

Kept the same model architecture and training parameters.

This adds a penalty to large weights to reduce overfitting.

Results Interpretation

Before regularization: Training accuracy was 98%, validation accuracy was 75%. The model was overfitting.

After adding L1 and L2 regularization: Training accuracy dropped to 90%, validation accuracy improved to 86%. Loss values also became more balanced.

Adding L1 and L2 regularization helps reduce overfitting by penalizing large weights, which improves the model's ability to generalize to new data.

Bonus Experiment

Try using only L1 regularization or only L2 regularization separately and compare the effects on overfitting and accuracy.

💡 Hint

Change the regularizer to regularizers.l1(0.001) or regularizers.l2(0.001) and observe the training and validation metrics.

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