__________ pruning is a technique where a decision tree is reduced by turning some branch nodes into leaf nodes.
- Cost Complexity
- Hybrid
- Random
- Reduced Error
Reduced Error Pruning is a technique where a decision tree is reduced by turning some branch nodes into leaf nodes and replacing them with the most common class. If this replacement does not reduce the accuracy on the validation set, the change is kept.
The concept of __________ in AI refers to the ability of a model to provide insight into its reasoning process, which may be more challenging in some Deep Learning models.
- generalization
- interpretability
- optimization
- reinforcement
Interpretability in AI refers to how understandable the model's reasoning process is, which can be more complex in some Deep Learning models.
In a situation where the data is densely packed in some regions and sparse in others, how would the choice of K and distance metric influence the results, and what would be the best approach?
- Choose a fixed K and Euclidean distance
- Choose a large K and any distance metric
- Choose a small K and ignore distance metric
- Choose an appropriate K and distance metric, considering data distribution
Considering the data distribution and choosing an appropriate value of K and distance metric can help address the issue of varying data density in KNN.
Why is centroid initialization important in K-Means clustering?
- All of the Above
- It determines the final clusters
- It prevents overfitting
- It speeds up the convergence process
Centroid initialization is important in K-Means as it can significantly affect the final clusters. Poor initialization can lead to suboptimal clusters or slow convergence.
Can you name a popular clustering algorithm used in Machine Learning?
- Decision Trees
- K-Means
- K-Nearest Neighbors
- Linear Regression
K-Means is a widely-used clustering algorithm that partitions data into K distinct, non-overlapping clusters based on similarity.
Logistic Regression is commonly used for __________ problems where the outcome has two categories.
- Binary classification
- Clustering
- Multiclass classification
- Regression
Logistic Regression is primarily used for binary classification problems where the outcome has only two categories.
Given a scenario where the feature correlation is very high, how would you choose between Ridge, Lasso, and ElasticNet?
- It doesn't matter
- Prefer ElasticNet
- Prefer Lasso
- Prefer Ridge
ElasticNet is preferred when there's multicollinearity, as it combines L1 and L2 penalties, balancing the properties of Ridge and Lasso.
In the context of Polynomial Regression, using too low a degree may lead to _________, while too high a degree may lead to _________.
- accuracy, inaccuracy
- overfitting, underfitting
- stability, instability
- underfitting, overfitting
Using too low a degree may cause the model to be too simple and underfit the data, while too high a degree can lead to a complex model that overfits the data.
Can classification be used to predict continuous values?
- No
- Only with specific algorithms
- Sometimes
- Yes
Classification is used to predict discrete categories or classes, not continuous values. Regression techniques are used for predicting continuous values.
In what way does Machine Learning support the pharmaceutical industry in drug discovery and development?
- Drug Discovery and Development
- Image Recognition
- Marketing Strategies
- Supply Chain Management
Machine Learning supports the pharmaceutical industry by analyzing biological data to predict potential drug interactions, identifying promising compounds, enhancing drug design, and accelerating the overall drug discovery and development process.