A) A method of controlling physical machines using human input. B) A type of software used for playing video games. C) A branch of artificial intelligence that enables machines to learn from data. D) A programming language used for designing computer chips.
A) Linear regression B) Classification C) Clustering D) Decision trees
A) Training the network using backpropagation. B) Introducing non-linearity to the network. C) Storing information for future use. D) Converting input to output directly.
A) Q-Learning B) K-Means C) Random Forest D) SVM
A) Decision Trees B) Naive Bayes C) Gradient Descent D) Principal Component Analysis (PCA)
A) Optimizes the model using backpropagation. B) Selects the best features for the model. C) Normalizes the data before training. D) Quantifies the difference between predicted and actual values.
A) Training a model without any data. B) The process of selecting and transforming input features to improve model performance. C) Regularizing the model to prevent overfitting. D) Evaluating the model using cross-validation.
A) To control the learning rate of the model. B) To add noise to the data. C) To minimize the loss function during training. D) To separate different classes in the input space.
A) Feature Scaling B) Batch Normalization C) Dropout D) Gradient Descent
A) Dimensionality reduction B) Classification C) Clustering D) Regression
A) Mean Absolute Error B) Mean squared error C) R-squared D) Accuracy
A) Imputation B) Duplicating the data C) Adding noise to the data D) Ignoring the missing data
A) AdaBoost B) PCA (Principal Component Analysis) C) K-nearest Neighbors (KNN) D) SMOTE (Synthetic Minority Over-sampling Technique)
A) K-means clustering B) Naive Bayes C) SVM (Support Vector Machine) D) Isolation Forest
A) Root Mean Squared Error (RMSE) B) Mean Squared Error (MSE) C) Log Loss D) Cross-entropy
A) Randomly selecting hyperparameters B) Ignoring hyperparameters C) Grid Search D) Focusing on a single hyperparameter
A) Cross-validation B) Using only training data C) Guessing D) Checking computational complexity
A) Random initialization B) Early stopping C) Batch normalization D) Backpropagation
A) Increasing the model complexity B) Removing key features C) Regularization D) Training the model on more data
A) The balance between training time and model performance. B) The balance between model complexity and generalizability. C) The tradeoff between underfitting and overfitting. D) The tradeoff between accuracy and precision.
A) Linear Regression B) Support Vector Machine (SVM) C) Principal Component Analysis (PCA) D) K-means clustering
A) K-means clustering B) Decision tree C) Principal component analysis D) Linear regression |