ML vs traditional programming in ML Python - Practice Questions

Challenge - 5 Problems

🧠 Conceptual

intermediate

Key difference between ML and traditional programming

Which statement best describes the main difference between machine learning and traditional programming?

A Machine learning does not need any input data to make decisions, unlike traditional programming.

B Machine learning always requires less data than traditional programming.

C Machine learning learns patterns from data, while traditional programming uses explicit rules written by humans.

D Traditional programming can automatically improve itself without human input, unlike machine learning.

❓ Predict Output

intermediate

Output of a simple ML prediction vs rule-based code

Given the following code snippets, what is the output of the machine learning model prediction compared to the traditional rule-based function?

ML Python

def rule_based(x):
    if x > 5:
        return 'High'
    else:
        return 'Low'

class SimpleModel:
    def predict(self, x):
        return 'High' if x > 3 else 'Low'

input_value = 4
print(rule_based(input_value))
model = SimpleModel()
print(model.predict(input_value))

A Low\nHigh

B Low\nLow

C High\nLow

D High\nHigh

❓ Model Choice

advanced

Choosing between ML and traditional programming for a task

You want to build a system that detects spam emails. Which approach is more suitable and why?

A Use machine learning because it can learn from examples and adapt to new spam types.

B Use traditional programming with fixed rules because spam patterns never change.

C Use traditional programming because it requires large amounts of labeled data.

D Use machine learning because it does not need any data to work.

❓ Metrics

advanced

Evaluating ML vs traditional programming accuracy

You test a traditional program and a machine learning model on 100 samples. The traditional program correctly classifies 80 samples, and the ML model correctly classifies 90 samples. What are their accuracies?

A Traditional: 0.8%, ML: 0.9%

B Traditional: 80%, ML: 90%

C Traditional: 90%, ML: 80%

D Traditional: 8%, ML: 9%

🔧 Debug

expert

Why does this ML model fail but traditional code works?

Given the code below, why does the machine learning model prediction raise an error while the traditional function works fine?

ML Python

def traditional_func(x):
    return 'Positive' if x > '0' else 'Non-positive'

class MLModel:
    def predict(self, x):
        return x > 0

input_value = '5'
print(traditional_func(input_value))
model = MLModel()
print(model.predict(input_value))

A The ML model fails because it returns a string instead of a boolean.

B The traditional function fails because it cannot handle strings.

C Both functions work fine with string input.

D The ML model fails because it tries to compare a string with an integer, causing a TypeError.