Error analysis patterns in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Identifying common causes of high training loss

Which of the following is least likely to cause a persistently high training loss in a TensorFlow model?

A Having a dataset with mislabeled examples in the training set

B Evaluating the model on the training data instead of validation data

C Using a model architecture that is too simple to capture the data patterns

D Using a learning rate that is too high, causing the model to overshoot minima

💡 Hint

Think about what affects training loss versus evaluation procedure.

Evaluating on training data does not cause high training loss; it just measures it. The other options directly cause the model to perform poorly during training.

❓ Predict Output

intermediate

Output of TensorFlow model predictions with incorrect input shape

What error will this TensorFlow code produce when running predictions?

import tensorflow as tf
model = tf.keras.Sequential([
  tf.keras.layers.Dense(5, activation='relu', input_shape=(3,))
])
model.compile(optimizer='adam', loss='mse')

import numpy as np
input_data = np.array([[1, 2]])  # Shape (1, 2), should be (1, 3)
predictions = model.predict(input_data)

A ValueError: Input 0 of layer sequential is incompatible with the layer: expected shape=(None, 3), found shape=(None, 2)

B TypeError: Unsupported operand type(s) for +: 'int' and 'str'

C No error, predictions will run and output shape (1, 5)

D RuntimeError: Model has not been compiled yet

💡 Hint

Check if the input shape matches the model's expected input shape.

The model expects input shape (None, 3) but receives (None, 2), causing a ValueError about incompatible input shape.

❓ Model Choice

advanced

Choosing a model to reduce overfitting detected in error analysis

You notice your TensorFlow model performs very well on training data but poorly on validation data. Which model change is most likely to reduce overfitting?

A Increase the number of layers and neurons to improve model capacity

B Remove batch normalization layers to simplify the model

C Add dropout layers to randomly disable neurons during training

D Use a smaller batch size during training

💡 Hint

Think about regularization techniques that prevent overfitting.

Dropout is a regularization method that helps reduce overfitting by randomly disabling neurons during training, forcing the model to generalize better.

❓ Metrics

advanced

Interpreting confusion matrix metrics for imbalanced data

Given a binary classification confusion matrix:

[[90, 10],
 [40, 60]]

Where rows are true classes and columns are predicted classes, what is the precision for the positive class?

A 0.857

B 0.4

C 0.6

D 0.75

💡 Hint

Precision = True Positives / (True Positives + False Positives)

True Positives = 60, False Positives = 10, so precision = 60 / (60 + 10) ≈ 0.857.

🔧 Debug

expert

Debugging exploding gradients in TensorFlow training

During training a deep neural network in TensorFlow, the loss suddenly becomes NaN after several epochs. Which debugging step is most effective to identify and fix exploding gradients?

A Increase the learning rate to speed up convergence

B Switch optimizer from Adam to SGD without momentum

C Remove dropout layers to stabilize training

D Add gradient clipping to limit the gradient values during backpropagation

💡 Hint

Exploding gradients cause very large updates; controlling gradient size helps.

Gradient clipping limits the size of gradients during backpropagation, preventing them from becoming too large and causing NaN loss.