Ml Development Quiz

Machine Learning Development Process Quiz

Question 1

Which of these is a way to do error analysis?

• Calculating the test error J_test
• Calculating the training error J_train
• Manually examine a sample of the training examples that the model misclassified in order to identify common traits and trends ✓
• Collecting additional training data in order to help the algorithm do better

Answer Location: Found in Section 2: Error analysis process “refers to manually looking through these 100 examples and trying to gain insights into where the algorithm is going wrong. Specifically, what I will often do is find a set of examples that the algorithm has misclassified examples from the cross validation set and try to group them into common teams or common properties or common traits.”

Question 2

We sometimes take an existing training example and modify it (for example, by rotating an image slightly) to create a new example with the same label. What is this process called?

• Machine learning diagnostic
• Bias/variance analysis
• Data augmentation ✓
• Error analysis

Answer Location: Found in Section 3: “This technique is called data augmentation. And what we’re going to do is take an existing training example to create a new training example.”

Question 3 (Multi-choice)

What are two possible ways to perform transfer learning? (Select two correct answers)

• ☐ Download a pre-trained model and use it for prediction without modifying or re-training it
• ☑ You can choose to train just the output layers’ parameters and leave the other parameters of the model fixed ✓
• ☐ Given a dataset, pre-train and then further fine tune a neural network on the same dataset
• ☑ You can choose to train all parameters of the model, including the output layers, as well as the earlier layers ✓

Answer Location: Found in Section 4: “In detail, there are two options for how you can train this neural networks parameters. Option 1 is you only train the output layers parameters… Option 2 would be to train all the parameters in the network including W^1, b^1, W^2, b^2 all the way through W^5, b^5 but the first four layers parameters would be initialized using the values that you had trained on top.”