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