Generative vs discriminative models in Prompt Engineering / GenAI - When to Use Which

The Big Idea

Discover how machines learn to both recognize and create, just like humans!

The Scenario

Imagine you want to sort thousands of photos into categories by hand, like "cats" or "dogs," and also create new photos that look like real animals. Doing this manually means looking at every photo carefully and trying to imagine new ones yourself.

The Problem

Sorting photos by hand is slow and tiring. Trying to create new realistic photos manually is almost impossible and full of mistakes. You can't easily guess what new photos should look like or quickly decide which category a photo belongs to.

The Solution

Generative and discriminative models help computers learn from examples to do these tasks automatically. Discriminative models learn to tell categories apart, like sorting photos quickly. Generative models learn how to create new examples that look real, like making new photos of animals.

Before vs After

✗ Before

if photo_has_cat(photo):
    label = 'cat'
else:
    label = 'dog'

✓ After

label = discriminative_model.predict(photo)
new_photo = generative_model.generate('cat')

What It Enables

These models let machines understand and create data, making tasks like image recognition and content creation fast and accurate.

Real Life Example

Apps that recognize your face to unlock your phone use discriminative models, while apps that create new art or deepfake videos use generative models.

Key Takeaways

Discriminative models focus on telling things apart.

Generative models focus on creating new, realistic data.

Together, they make powerful tools for understanding and generating information.

Practice

1. Which statement best describes a generative model in machine learning?

easy

A. It only works with labeled data for prediction.

B. It directly learns the boundary between classes for classification.

C. It learns how data is generated and can create new examples.

D. It ignores the data distribution and focuses on accuracy.

Solution

1. Step 1: Understand generative model purpose

   Generative models learn the underlying data distribution to generate new data points similar to the training data.

2. Step 2: Compare with discriminative models

   Discriminative models focus on learning the decision boundary between classes, not on generating data.

3. Final Answer:

   It learns how data is generated and can create new examples. -> Option C

4. Quick Check:

   Generative = create data [OK]

Hint: Generative models create data; discriminative separate classes [OK]

Common Mistakes:

• Confusing generative with discriminative models
• Thinking generative models only classify
• Assuming generative models ignore data distribution

2. Which of the following is the correct way to describe a discriminative model?

easy

A. It models the conditional probability of outputs given inputs.

B. It ignores labels and focuses on data generation.

C. It generates new data points similar to training data.

D. It models the joint probability of inputs and outputs.

Solution

1. Step 1: Define discriminative model behavior

   Discriminative models learn the conditional probability P(output|input), focusing on predicting labels from data.

2. Step 2: Contrast with generative models

   Generative models model the joint probability P(input, output) to generate data, which is not the case here.

3. Final Answer:

   It models the conditional probability of outputs given inputs. -> Option A

4. Quick Check:

   Discriminative = P(output|input) [OK]

Hint: Discriminative models predict labels from inputs [OK]

Common Mistakes:

• Mixing joint and conditional probabilities
• Thinking discriminative models generate data
• Confusing labels with data points

3. Consider the following Python code snippet using scikit-learn:

from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import LogisticRegression

X_train = [[1, 2], [2, 3], [3, 4], [4, 5]]
y_train = [0, 0, 1, 1]

model = GaussianNB()
model.fit(X_train, y_train)
predictions = model.predict([[2, 3]])
print(predictions)

What will be the output of this code?

medium

A. [1]

B. [0]

C. [0 1]

D. Error due to wrong model usage

Solution

1. Step 1: Identify model type and training data

   GaussianNB is a generative model that learns class distributions. Training data has two classes: 0 and 1.

2. Step 2: Predict class for input [2, 3]

   Input [2, 3] is closer to training points labeled 0 ([1,2],[2,3]) than to those labeled 1, so prediction is class 0.

3. Final Answer:

   [0] -> Option B

4. Quick Check:

   GaussianNB predicts class 0 for [2,3] [OK]

Hint: GaussianNB predicts class based on closest learned distribution [OK]

Common Mistakes:

• Assuming LogisticRegression is used instead
• Expecting multiple classes in output
• Thinking prediction causes error

4. The following code tries to train a discriminative model but has an error:

from sklearn.linear_model import LogisticRegression

X_train = [[1, 2], [2, 3], [3, 4]]
y_train = [0, 1]

model = LogisticRegression()
model.fit(X_train, y_train)

What is the error and how to fix it?

medium

A. Mismatch in number of samples and labels; fix by matching lengths.

B. LogisticRegression requires numeric labels; convert labels to numbers.

C. X_train must be a numpy array; convert list to array.

D. Model.fit() missing parameter; add sample weights.

Solution

1. Step 1: Check training data shapes

   X_train has 3 samples, but y_train has only 2 labels, causing mismatch error.

2. Step 2: Fix label length

   To fix, ensure y_train has 3 labels matching X_train samples, e.g., y_train = [0, 1, 0].

3. Final Answer:

   Mismatch in number of samples and labels; fix by matching lengths. -> Option A

4. Quick Check:

   Samples and labels count must match [OK]

Hint: Check if data and label counts match before training [OK]

Common Mistakes:

• Ignoring label count mismatch
• Assuming LogisticRegression needs label conversion
• Thinking data type causes error

5. You want to build a model that can both classify images of cats and dogs and also generate new realistic images of cats. Which approach should you choose?

hard

A. Use a clustering algorithm to separate and generate images.

B. Use a generative model like a Generative Adversarial Network (GAN) for both tasks.

C. Use a discriminative model like Logistic Regression for both tasks.

D. Use a discriminative model for classification and a generative model for image creation.

Solution

1. Step 1: Identify tasks and suitable models

   Classification is best done by discriminative models that separate classes well. Image generation requires generative models that learn data distribution.

2. Step 2: Combine models for both tasks

   Use a discriminative model for classifying cats vs dogs, and a generative model like GAN to create new cat images.

3. Final Answer:

   Use a discriminative model for classification and a generative model for image creation. -> Option D

4. Quick Check:

   Classification + generation = discriminative + generative [OK]

Hint: Classify with discriminative, generate with generative models [OK]

Common Mistakes:

• Using one model type for both tasks
• Confusing clustering with generation
• Ignoring model strengths for each task