GDSC AI ML Session

Which icon represents Seaborn correctly from the options provided?

• 
• 
• 
• 
• 

In decision tree pruning, what is the purpose of the tuning parameter (often denoted as alpha or ccp_alpha)?

• To control the learning rate of the decision tree

• To balance the trade-off between tree complexity and impurity reduction.

• To adjust the minimum number of samples required to split a node.

• To set the maximum depth of the decision tree.

When growing a decision tree, the algorithm selects the best feature to split on at each node. What criterion is commonly used to measure the "best" split?

• Mean Squared Error (MSE)

• Gini impurity

• Accuracy

• Information gain

You are tasked with building a decision tree for a binary classification problem. After constructing the tree, you notice that it has a depth of 25, and the training accuracy is 100%. However, when you evaluate the model on a separate test set, the accuracy drops significantly. What is the most likely reason for this discrepancy?

• The model suffered from data leakage during training.

• The tree is too shallow to capture the complexity of the data.

• The model has overfit the training data.

• The test set is not representative of the training data.

Explain the concept of decision trees in machine learning and how they handle feature selection during the learning process.

• Features are ranked based on importance, and the tree chooses the best feature for splitting

• Decision trees select features randomly at each node to promote diversity

• Decision trees use all features during each split to maximize information gain

• Decision trees only consider the target variable for feature selection

What is the purpose of the term "dropout" in the training process of neural networks, and how does it contribute to model generalization?

• Dropout refers to removing irrelevant features during model training to reduce complexity

• It is a technique for randomly deactivating neurons during training to prevent overfitting

• Dropout is a regularization method specifically applied to convolutional neural networks

• It denotes the gradual decrease in learning rate over epochs for stable convergence

What is the primary advantage of using Random Forest over a single Decision Tree in terms of predictive performance?

• Reduced bias

• Lower variance

• Improved interpretability

• Faster training time

How does the Random Forest algorithm handle overfitting compared to a deep Decision Tree?

• Random Forest is more prone to overfitting

• Decision Trees are immune to overfitting

• Random Forest mitigates overfitting by aggregating predictions

• Overfitting is equally likely in both Random Forest and Decision Trees

What significant event in 1956 is considered the birth of artificial intelligence, bringing together prominent researchers and sparking the establishment of AI as a field of study?

• The development of the first perceptron

• The Dartmouth Workshop

• The publication of the Turing Test

• The introduction of backpropagation algorithm

Which icon represents Matplotlib correctly from the options provided?

• 
• 
• 
• 
•