1.) We want to build a model to predict the weight (in Ibs) of a car. This prediction will be based on multiple features of the car, such as: "Number of Cylinders", "Miles Per Gallon", "Production...

Extracted text: 1.) We want to build a model to predict the weight (in Ibs) of a car. This prediction will be based on multiple features of the car, such as: "Number of Cylinders", "Miles Per Gallon", "Production Year", etc. To train the model, we are given 1000 examples of cars along with the feature values and class for each car. What technique could we use in this case? Multiple Linear Regression Simple Linear Regression O K-Means Clustering K-Nearest Neighbors


Extracted text: 4.) Suppose you are trying to tune a classification algorithm and you try several different hyper- parameter settings. These are the different results you obtain. Which one of them is likely to be overfitting? Training Accuracy330% and Test Accuracy=32% O Training Accuracy=97% and Test Accuracy=77% Training Accuracy380% and Test Accuracy=75%