Comprehensive AI Questions and Answers: Multiple-Choice Practice Test
What is Artificial Intelligence (AI)?
Answer: AI refers to the development of computer programs that can perform tasks that typically require human intelligence, such as perception, reasoning, and learning.
What are the two primary types of machine learning?
Answer: The two primary types of machine learning are supervised learning and unsupervised learning.
What is reinforcement learning?
Answer: Reinforcement learning is a type of machine learning that involves an agent interacting with an environment and learning to make decisions that maximize a reward signal.
What is a neural network?
Answer: A neural network is a type of machine learning model that is designed to simulate the structure and function of the human brain.
What is natural language processing (NLP)?
Answer: Natural language processing (NLP) is a subfield of AI that focuses on the interactions between computers and human language, including tasks such as language translation and sentiment analysis.
What is computer vision?
Answer: Computer vision is a subfield of AI that focuses on enabling computers to interpret and understand visual information from the world, such as images and videos.
What is the difference between strong AI and weak AI?
Answer: Strong AI refers to the development of machines that are capable of performing any intellectual task that a human can do, while weak AI refers to the development of machines that can only perform specific tasks or simulate human intelligence in a limited way.
What is deep learning?
Answer: Deep learning is a subset of machine learning that involves the use of deep neural networks with multiple layers to learn from large amounts of data and make predictions or decisions.
What is the difference between a convolutional neural network (CNN) and a recurrent neural network (RNN)?
Answer: A CNN is designed for image processing and feature extraction, while an RNN is designed for sequential data and can capture long-term dependencies between data points. RNNs are commonly used for natural language processing and speech recognition, while CNNs are commonly used for image recognition and object detection.
What is the difference between supervised and unsupervised learning?
Answer: Supervised learning involves training a model on labeled data, where the correct outputs are known, while unsupervised learning involves training a model on unlabeled data, where the correct outputs are unknown. Supervised learning is commonly used for classification and regression tasks, while unsupervised learning is commonly used for clustering and anomaly detection.
What is transfer learning?
Answer: Transfer learning is a technique where a pre-trained model is used as a starting point for a new task, rather than training a new model from scratch. Transfer learning can be useful when the amount of available data for a new task is limited, as it allows the model to leverage knowledge gained from previous tasks.
What is the bias-variance tradeoff?
Answer: The bias-variance tradeoff refers to the tradeoff between a model’s ability to fit the training data (bias) and its ability to generalize to new data (variance). A model with high bias is underfitting the data and may not capture all of the relevant information, while a model with high variance is overfitting the data and may be too complex and not generalize well to new data.
What is the difference between model-based and model-free reinforcement learning?
Answer: Model-based reinforcement learning involves using a model of the environment to learn an optimal policy, while model-free reinforcement learning does not use a model and learns directly from experience. Model-based reinforcement learning can be more sample-efficient but requires accurate models of the environment, while model-free reinforcement learning is more flexible but can be more data-intensive.
What is adversarial training?
Answer: Adversarial training is a technique where a model is trained on adversarial examples, which are generated by intentionally perturbing input data to cause misclassification. Adversarial training can improve a model’s robustness to small changes in the input data and improve its performance on real-world data.
What is attention mechanism?
Answer: Attention mechanism is a mechanism used in deep learning where the model learns to focus on different parts of the input data at different times, based on their relevance to the task at hand. Attention mechanisms can improve a model’s ability to process long sequences of data and can be used in natural language processing, speech recognition, and other tasks.
What is the difference between a generative model and a discriminative model?
Answer: A generative model learns the joint probability distribution of the input data and the labels, while a discriminative model learns the conditional probability distribution of the labels given the input data. Generative models can be used for tasks such as image generation and data synthesis, while discriminative models are commonly used for classification tasks.
What is a GAN (Generative Adversarial Network)?
Answer: A GAN is a type of generative model that consists of two neural networks: a generator and a discriminator. The generator generates fake data samples, while the discriminator tries to distinguish between the fake and real data samples. The two networks are trained together in an adversarial process until the generator produces realistic data samples.
What is reinforcement learning with deep neural networks?
Answer: Reinforcement learning with deep neural networks involves using deep neural networks to approximate the Q-function or policy function in a reinforcement learning problem. Deep reinforcement learning can be used to solve complex problems with high-dimensional inputs, such as playing Atari games or controlling robots.
What is meta-learning?
Answer: Meta-learning, also known as “learning to learn,” is a technique where a model is trained to learn how to learn new tasks more efficiently. Meta-learning can be used to improve the sample efficiency of machine learning algorithms, allowing them to learn from fewer examples.
What is explainable AI (XAI)?
Answer: Explainable AI refers to the development of AI systems that can provide understandable explanations for their decisions and actions. XAI is important for building trust and transparency in AI systems, and can be useful in domains such as healthcare, finance, and law.
What is unsupervised representation learning?
Answer: Unsupervised representation learning involves learning representations of data without using explicit labels or annotations. Unsupervised representation learning can be used for tasks such as clustering, anomaly detection, and data compression, and can be useful in domains such as natural language processing and computer vision.
What is a transformer network?
Answer: A transformer network is a type of neural network architecture that is commonly used in natural language processing tasks such as language translation and sentiment analysis. Transformer networks use a self-attention mechanism to selectively weigh different parts of the input sequence, allowing them to process long sequences of data more efficiently.
What is the difference between a generative model and a discriminative model?
Answer: A generative model learns the joint probability distribution of the input data and the labels, while a discriminative model learns the conditional probability distribution of the labels given the input data. Generative models can be used for tasks such as image generation and data synthesis, while discriminative models are commonly used for classification tasks.
What is a GAN (Generative Adversarial Network)?
Answer: A GAN is a type of generative model that consists of two neural networks: a generator and a discriminator. The generator generates fake data samples, while the discriminator tries to distinguish between the fake and real data samples. The two networks are trained together in an adversarial process until the generator produces realistic data samples.
What is reinforcement learning with deep neural networks?
Answer: Reinforcement learning with deep neural networks involves using deep neural networks to approximate the Q-function or policy function in a reinforcement learning problem. Deep reinforcement learning can be used to solve complex problems with high-dimensional inputs, such as playing Atari games or controlling robots.
What is meta-learning?
Answer: Meta-learning, also known as “learning to learn,” is a technique where a model is trained to learn how to learn new tasks more efficiently. Meta-learning can be used to improve the sample efficiency of machine learning algorithms, allowing them to learn from fewer examples.
What is explainable AI (XAI)?
Answer: Explainable AI refers to the development of AI systems that can provide understandable explanations for their decisions and actions. XAI is important for building trust and transparency in AI systems, and can be useful in domains such as healthcare, finance, and law.
What is unsupervised representation learning?
Answer: Unsupervised representation learning involves learning representations of data without using explicit labels or annotations. Unsupervised representation learning can be used for tasks such as clustering, anomaly detection, and data compression, and can be useful in domains such as natural language processing and computer vision.
What is a transformer network?
Answer: A transformer network is a type of neural network architecture that is commonly used in natural language processing tasks such as language translation and sentiment analysis. Transformer networks use a self-attention mechanism to selectively weigh different parts of the input sequence, allowing them to process long sequences of data more efficiently.
What is the difference between supervised, unsupervised, and reinforcement learning?
Answer: Supervised learning is a machine learning technique where a model learns from labeled examples to make predictions on new, unseen data. Unsupervised learning involves learning patterns in data without explicit labels or annotations. Reinforcement learning involves learning how to take actions in an environment to maximize a reward signal. Supervised learning is used for tasks such as image classification and object detection, unsupervised learning is used for tasks such as clustering and dimensionality reduction, and reinforcement learning is used for tasks such as game playing and robotic control.
What is a neural network and how does it work?
Answer: A neural network is a type of machine learning algorithm that is inspired by the structure and function of the brain. A neural network consists of layers of artificial neurons that are connected by weights. During training, the weights are adjusted to minimize a loss function, allowing the network to learn patterns in the data. Neural networks are commonly used for tasks such as image classification, speech recognition, and natural language processing.
What is deep learning and how does it differ from traditional machine learning?
Answer: Deep learning is a subset of machine learning that involves using deep neural networks with many layers to learn hierarchical representations of data. Deep learning differs from traditional machine learning in that it can automatically learn complex features from raw data, without the need for manual feature engineering. Deep learning has been used to achieve state-of-the-art performance on tasks such as image recognition, speech recognition, and natural language processing.
What is a convolutional neural network (CNN) and how is it used in image recognition?
Answer: A convolutional neural network is a type of neural network that is commonly used for image recognition tasks. CNNs use a series of convolutional layers to learn local features in the input image, followed by a series of fully connected layers to classify the image. CNNs have achieved state-of-the-art performance on tasks such as object detection, face recognition, and image segmentation.
What is a recurrent neural network (RNN) and how is it used in natural language processing?
Answer: A recurrent neural network is a type of neural network that is commonly used for natural language processing tasks such as language modeling and machine translation. RNNs use a series of recurrent layers to model the sequential nature of text data. RNNs have achieved state-of-the-art performance on tasks such as language modeling, machine translation, and speech recognition.
What is a self-organizing map (SOM) and how is it used in unsupervised learning?
Answer: A self-organizing map is a type of neural network that is commonly used for unsupervised learning tasks such as clustering and visualization. SOMs use a competitive learning algorithm to learn a low-dimensional representation of the input data. SOMs have been used for tasks such as image segmentation, speech recognition, and anomaly detection.
What is transfer learning and how is it used in machine learning?
Answer: Transfer learning is a technique in machine learning where knowledge learned in one task is applied to a new, related task. Transfer learning can be used to improve the performance of a model on a new task with limited data by leveraging knowledge learned from a related task with more data. Transfer learning has been used for tasks such as image recognition, speech recognition, and natural language processing.
What is the difference between a generative and discriminative model in machine learning?
Answer: A generative model learns the joint probability distribution of the input and output data, and can be used to generate new samples of the data. A discriminative model learns the conditional probability distribution of the output given the input data, and is used to make predictions about the output given new input data. Generative models are used for tasks such as image generation and speech synthesis, while discriminative models are used for tasks such as classification and regression.
What is a Bayesian network and how is it used in probabilistic inference?
Answer: A Bayesian network is a graphical model that represents the joint probability distribution of a set of random variables. Bayesian networks can be used to perform probabilistic inference, which involves calculating the probability of one or more variables given evidence about other variables. Bayesian networks have been used for tasks such as diagnosis and decision making.
What is deep reinforcement learning and how is it used in robotics?
Answer: Deep reinforcement learning is a type of machine learning that combines deep learning with reinforcement learning to learn complex behaviors in robotics. Deep reinforcement learning involves using deep neural networks to approximate the value function or policy of an agent in a given environment. Deep reinforcement learning has been used for tasks such as robotic control, game playing, and autonomous driving.
What is the difference between model-based and model-free reinforcement learning?
Answer: Model-based reinforcement learning involves learning a model of the environment in addition to the value function or policy. The learned model can be used to simulate future states and rewards, which can be used to plan optimal actions. Model-free reinforcement learning, on the other hand, does not learn a model of the environment and instead learns the value function or policy directly from experience. Model-based reinforcement learning can be more sample-efficient but requires additional computation, while model-free reinforcement learning is simpler but can be less efficient.
What is a transformer network and how is it used in natural language processing?
Answer: A transformer network is a type of neural network that is commonly used for natural language processing tasks such as machine translation and language modeling. Transformer networks use self-attention mechanisms to model the relationships between different parts of a sequence, allowing them to capture long-range dependencies more effectively than traditional recurrent neural networks. Transformer networks have achieved state-of-the-art performance on tasks such as machine translation, language modeling, and question answering.
What is a variational autoencoder (VAE) and how is it used in unsupervised learning?
Answer: A variational autoencoder is a type of generative model that is commonly used for unsupervised learning tasks such as image generation and data compression. VAEs use a neural network encoder to map the input data to a low-dimensional latent space, and a decoder network to generate new samples of the data. VAEs use a variational inference algorithm to learn the parameters of the model, allowing them to generate high-quality samples of the data.
What is transfer learning and how is it used in deep learning?
Answer: Transfer learning is a technique in deep learning that involves using a pre-trained neural network to solve a new task. The pre-trained neural network is typically trained on a large, general dataset such as ImageNet, and then fine-tuned on the specific task at hand using a smaller dataset. Transfer learning can significantly reduce the amount of data required to train a neural network and can improve its performance.
What is the difference between supervised, unsupervised, and semi-supervised learning?
Answer: Supervised learning is a type of machine learning that involves learning a function that maps input data to output data using labeled training data. Unsupervised learning is a type of machine learning that involves learning patterns and structure in the data without using labeled data. Semi-supervised learning is a combination of both supervised and unsupervised learning, where the model is trained using a mix of labeled and unlabeled data. Supervised learning is commonly used for tasks such as classification and regression, while unsupervised learning is used for tasks such as clustering and anomaly detection.
What is adversarial training and how is it used in deep learning?
Answer: Adversarial training is a technique in deep learning that involves training a neural network to be robust to adversarial attacks. Adversarial attacks involve adding small, imperceptible perturbations to the input data that can cause the neural network to misclassify the data. Adversarial training involves generating adversarial examples during the training process and using them to train the neural network to be more robust to such attacks.
What is a recurrent neural network (RNN) and how is it used in natural language processing?
Answer: A recurrent neural network is a type of neural network that is commonly used for natural language processing tasks such as language modeling and machine translation. RNNs use a feedback loop to allow information to persist across multiple time steps, allowing them to model sequential data such as text. RNNs have been used for tasks such as machine translation, language modeling, and speech recognition.
What is a convolutional neural network (CNN) and how is it used in computer vision?
Answer: A convolutional neural network is a type of neural network that is commonly used for computer vision tasks such as object detection and image classification. CNNs use convolutional layers to extract features from the input data, allowing them to learn hierarchical representations of the data. CNNs have been used for tasks such as object detection, image classification, and image segmentation.
What is reinforcement learning and how is it used in robotics?
Answer: Reinforcement learning is a type of machine learning that involves learning an optimal policy for an agent to take actions in an environment based on rewards or penalties. Reinforcement learning has been used for tasks such as robotic control, game playing, and autonomous driving. In robotics, reinforcement learning can be used to learn complex behaviors such as grasping, manipulation, and navigation.
What is the difference between deep learning and machine learning?
Answer: Deep learning is a subfield of machine learning that involves using neural networks with multiple layers to learn hierarchical representations of the data. Machine learning is a broader field that includes many different types of algorithms, including neural networks. Deep learning has been particularly successful in recent years for tasks such as image and speech recognition.
What is the curse of dimensionality and how does it affect machine learning algorithms?
Answer: The curse of dimensionality refers to the difficulty that machine learning algorithms face when trying to learn from high-dimensional data. As the number of dimensions in the data increases, the amount of data required to learn a model that generalizes well increases exponentially. This can lead to overfitting, where the model fits the training data well but does not generalize well to new data. To address the curse of dimensionality, techniques such as feature selection, dimensionality reduction, and regularization are often used.
What is the difference between batch learning and online learning?
Answer: Batch learning involves training a model on a fixed dataset and then using the trained model to make predictions on new data. Online learning, on the other hand, involves updating the model continuously as new data becomes available. Batch learning can be computationally efficient but may not be well-suited for tasks where the data is constantly changing. Online learning is well-suited for tasks such as recommendation systems and fraud detection, where the data is constantly changing.
What is generative adversarial networks (GANs) and how are they used in machine learning?
Answer: Generative adversarial networks are a type of neural network that consists of two components: a generator and a discriminator. The generator generates samples that are intended to be similar to real data, while the discriminator distinguishes between real and fake data. During training, the generator and discriminator are trained together in a game-like setting, where the generator tries to generate samples that can fool the discriminator, and the discriminator tries to correctly distinguish between real and fake data. GANs have been used for tasks such as image and video generation.
What is reinforcement learning and how is it used in game playing?
Answer: Reinforcement learning is a type of machine learning that involves learning an optimal policy for an agent to take actions in an environment based on rewards or penalties. In game playing, reinforcement learning can be used to learn to play games such as chess and Go at a superhuman level. Reinforcement learning has also been used to develop agents that can play video games such as Atari games and first-person shooter games.
AI multiple Questions and Answers
Which of the following is a supervised learning algorithm? a) K-means clustering b) Decision tree c) Principal Component Analysis d) Apriori algorithm
Answer: b) Decision tree
Which of the following is a deep learning framework? a) TensorFlow b) Naive Bayes c) K-means clustering d) Random forest
Answer: a) TensorFlow
Which of the following is a reinforcement learning algorithm? a) K-nearest neighbors b) Support vector machines c) Q-learning d) Linear regression
Answer: c) Q-learning
Which of the following is a technique used for dimensionality reduction? a) K-means clustering b) Support vector machines c) Random forest d) Principal Component Analysis
Answer: d) Principal Component Analysis
Which of the following is a type of unsupervised learning algorithm? a) K-nearest neighbors b) Decision tree c) K-means clustering d) Support vector machines
Answer: c) K-means clustering
Which of the following is a type of neural network commonly used for image recognition? a) Convolutional neural network b) Recurrent neural network c) Multilayer perceptron d) Deep belief network
Answer: a) Convolutional neural network
Which of the following is a technique used for handling imbalanced datasets? a) Oversampling b) Undersampling c) SMOTE d) All of the above
Answer: d) All of the above
Which of the following is a commonly used evaluation metric for classification tasks? a) Mean squared error b) F1 score c) R squared d) Adjusted R squared
Answer: b) F1 score
Which of the following is a technique used for feature selection? a) Principal Component Analysis b) Recursive feature elimination c) Regularization d) All of the above
Answer: d) All of the above
Which of the following is a commonly used optimization algorithm for training neural networks? a) Gradient descent b) Naive Bayes c) K-means clustering d) Random forest
Answer: a) Gradient descent
These are just a few examples of multiple-choice questions with answers related to AI. Keep in mind that there are many different topics and concepts within AI, and these questions are just a small sample. It’s important to have a broad understanding of the field and be able to apply concepts and techniques to different problems.
Which of the following is a technique used for natural language processing? a) K-means clustering b) Decision tree c) Word embedding d) Apriori algorithm
Answer: c) Word embedding
Which of the following is a technique used for anomaly detection? a) Principal Component Analysis b) K-nearest neighbors c) Random forest d) Isolation Forest
Answer: d) Isolation Forest
Which of the following is a type of neural network commonly used for sequential data processing? a) Convolutional neural network b) Recurrent neural network c) Multilayer perceptron d) Deep belief network
Answer: b) Recurrent neural network
Which of the following is a technique used for hyperparameter tuning? a) Grid search b) Random search c) Bayesian optimization d) All of the above
Answer: d) All of the above
Which of the following is a commonly used loss function for regression tasks? a) Cross-entropy b) Hinge loss c) Mean squared error d) F1 score
Answer: c) Mean squared error
Which of the following is a technique used for reducing overfitting in a neural network? a) Dropout b) Batch normalization c) L2 regularization d) All of the above
Answer: d) All of the above
Which of the following is a technique used for handling missing data in a dataset? a) Mean imputation b) Median imputation c) KNN imputation d) All of the above
Answer: d) All of the above
Which of the following is a technique used for time series forecasting? a) ARIMA b) K-means clustering c) Decision tree d) Naive Bayes
Answer: a) ARIMA
Which of the following is a commonly used evaluation metric for regression tasks? a) Mean squared error b) F1 score c) AUC-ROC d) Precision-Recall curve
Answer: a) Mean squared error
Which of the following is a technique used for data preprocessing in a neural network? a) Normalization b) Standardization c) One-hot encoding d) All of the above
Answer: d) All of the above
Which of the following is a commonly used activation function in a neural network? a) Sigmoid b) Linear c) ReLU d) All of the above
Answer: d) All of the above
Which of the following is a technique used for dimensionality reduction? a) Principal Component Analysis b) K-means clustering c) Random forest d) Gradient boosting
Answer: a) Principal Component Analysis
Which of the following is a commonly used optimization algorithm for training a neural network? a) Stochastic Gradient Descent b) Gradient Boosting c) Random Forest d) K-means clustering
Answer: a) Stochastic Gradient Descent
Which of the following is a technique used for image segmentation? a) K-means clustering b) Convolutional neural network c) Decision tree d) Naive Bayes
Answer: b) Convolutional neural network
Which of the following is a technique used for data augmentation in computer vision tasks? a) Random crop b) Random rotation c) Flipping d) All of the above
Answer: d) All of the above
Which of the following is a commonly used loss function for classification tasks? a) Mean squared error b) Cross-entropy c) Hinge loss d) F1 score
Answer: b) Cross-entropy
Which of the following is a commonly used algorithm for clustering? a) K-nearest neighbors b) K-means clustering c) Decision tree d) Naive Bayes
Answer: b) K-means clustering
Which of the following is a technique used for text classification? a) Bag of words b) K-means clustering c) Decision tree d) Naive Bayes
Answer: a) Bag of words
Which of the following is a commonly used algorithm for reinforcement learning? a) Q-learning b) K-nearest neighbors c) Decision tree d) Naive Bayes
Answer: a) Q-learning
Which of the following is a technique used for transfer learning in a neural network? a) Fine-tuning b) Dropout c) Regularization d) All of the above
Answer: a) Fine-tuning
Which of the following are examples of supervised learning algorithms? (Select all that apply) a) K-means clustering b) Decision tree c) Random forest d) Naive Bayes e) Support vector machine (SVM)
Answer: b) Decision tree, c) Random forest, d) Naive Bayes, e) Support vector machine (SVM)
Which of the following are examples of unsupervised learning algorithms? (Select all that apply) a) K-means clustering b) Decision tree c) Random forest d) Naive Bayes e) Support vector machine (SVM)
Answer: a) K-means clustering
Which of the following are techniques used for regularization in a neural network? (Select all that apply) a) Dropout b) L1 regularization c) L2 regularization d) Batch normalization
Answer: a) Dropout, b) L1 regularization, c) L2 regularization
Which of the following are commonly used neural network architectures for image recognition tasks? (Select all that apply) a) Convolutional neural network (CNN) b) Recurrent neural network (RNN) c) Generative adversarial network (GAN) d) Autoencoder
Answer: a) Convolutional neural network (CNN), d) Autoencoder
Which of the following are techniques used for hyperparameter tuning in a machine learning model? (Select all that apply) a) Grid search b) Random search c) Bayesian optimization d) Genetic algorithm
Answer: a) Grid search, b) Random search, c) Bayesian optimization, d) Genetic algorithm
Which of the following are commonly used activation functions in a neural network? (Select all that apply) a) Sigmoid b) Linear c) ReLU d) Softmax
Answer: a) Sigmoid, c) ReLU, d) Softmax
Which of the following are techniques used for data preprocessing in a machine learning model? (Select all that apply) a) Standardization b) Normalization c) One-hot encoding d) PCA (Principal Component Analysis)
Answer: a) Standardization, b) Normalization, c) One-hot encoding, d) PCA (Principal Component Analysis)
Which of the following are commonly used loss functions in a neural network for regression tasks? (Select all that apply) a) Mean squared error b) Mean absolute error c) Huber loss d) Binary cross-entropy
Answer: a) Mean squared error, b) Mean absolute error, c) Huber loss
Which of the following are commonly used algorithms for natural language processing (NLP)? (Select all that apply) a) Bag of words b) Recurrent neural network (RNN) c) Transformer d) Decision tree
Answer: a) Bag of words, b) Recurrent neural network (RNN), c) Transformer
Which of the following are commonly used techniques for feature selection in a machine learning model? (Select all that apply) a) Recursive feature elimination b) Principal Component Analysis (PCA) c) Mutual information d) Random forest feature importance
Answer: a) Recursive feature elimination, b) Principal Component Analysis (PCA), c) Mutual information, d) Random forest feature importance
AI Multiple-choice Questions with Multiple Answer
Which of the following are commonly used techniques for dimensionality reduction in a machine learning model? (Select all that apply) a) Principal Component Analysis (PCA) b) Singular Value Decomposition (SVD) c) Linear Discriminant Analysis (LDA) d) Independent Component Analysis (ICA)
Answer: a) Principal Component Analysis (PCA), b) Singular Value Decomposition (SVD), d) Independent Component Analysis (ICA)
Which of the following are commonly used deep learning frameworks? (Select all that apply) a) TensorFlow b) PyTorch c) Keras d) Caffe
Answer: a) TensorFlow, b) PyTorch, c) Keras, d) Caffe
Which of the following are commonly used reinforcement learning algorithms? (Select all that apply) a) Q-Learning b) Deep Q-Network (DQN) c) Actor-Critic d) Support vector machine (SVM)
Answer: a) Q-Learning, b) Deep Q-Network (DQN), c) Actor-Critic
Which of the following are commonly used clustering algorithms? (Select all that apply) a) K-means clustering b) Hierarchical clustering c) Density-based spatial clustering of applications with noise (DBSCAN) d) Gradient descent
Answer: a) K-means clustering, b) Hierarchical clustering, c) Density-based spatial clustering of applications with noise (DBSCAN)
Which of the following are commonly used natural language processing (NLP) techniques for text classification tasks? (Select all that apply) a) Bag of words b) Recurrent neural network (RNN) c) Convolutional neural network (CNN) d) Word embeddings
Answer: a) Bag of words, c) Convolutional neural network (CNN), d) Word embeddings
Which of the following are commonly used techniques for anomaly detection in a machine learning model? (Select all that apply) a) Isolation Forest b) One-Class SVM c) Autoencoder d) Decision tree
Answer: a) Isolation Forest, b) One-Class SVM, c) Autoencoder
Which of the following are commonly used techniques for image segmentation tasks? (Select all that apply) a) K-means clustering b) Region-based segmentation c) Convolutional neural network (CNN) d) Active contour models
Answer: b) Region-based segmentation, c) Convolutional neural network (CNN), d) Active contour models
Which of the following are commonly used techniques for handling missing values in a dataset? (Select all that apply) a) Mean imputation b) Median imputation c) Mode imputation d) Multiple imputation
Answer: a) Mean imputation, b) Median imputation, c) Mode imputation, d) Multiple imputation
Which of the following are commonly used deep learning architectures for natural language processing (NLP) tasks? (Select all that apply) a) Recurrent neural network (RNN) b) Convolutional neural network (CNN) c) Transformer d) Multilayer perceptron (MLP)
Answer: a) Recurrent neural network (RNN), b) Convolutional neural network (CNN), c) Transformer
Which of the following are commonly used techniques for handling imbalanced datasets in a machine learning model? (Select all that apply) a) Undersampling b) Oversampling c) Synthetic minority oversampling technique (SMOTE) d) Random forest
Answer: a) Undersampling,
Which of the following are commonly used regularization techniques in a machine learning model? (Select all that apply) a) L1 regularization b) L2 regularization c) Dropout d) Gradient descent
Answer: a) L1 regularization, b) L2 regularization, c) Dropout
Which of the following are commonly used techniques for object detection tasks in computer vision? (Select all that apply) a) Region-based convolutional neural network (R-CNN) b) Single Shot Detector (SSD) c) You Only Look Once (YOLO) d) Gradient descent
Answer: a) Region-based convolutional neural network (R-CNN), b) Single Shot Detector (SSD), c) You Only Look Once (YOLO)
Which of the following are commonly used techniques for data preprocessing in machine learning? (Select all that apply) a) Feature scaling b) Feature encoding c) Feature normalization d) Feature extraction
Answer: a) Feature scaling, b) Feature encoding, c) Feature normalization, d) Feature extraction
Which of the following are commonly used techniques for text data cleaning in natural language processing (NLP)? (Select all that apply) a) Lowercasing b) Removing stop words c) Stemming d) Random forest
Answer: a) Lowercasing, b) Removing stop words, c) Stemming
Which of the following are commonly used techniques for time series forecasting? (Select all that apply) a) Autoregressive Integrated Moving Average (ARIMA) b) Long Short-Term Memory (LSTM) c) Support vector machine (SVM) d) Gradient descent
Answer: a) Autoregressive Integrated Moving Average (ARIMA), b) Long Short-Term Memory (LSTM), c) Support vector machine (SVM)
Which of the following are commonly used techniques for model evaluation in machine learning? (Select all that apply) a) Confusion matrix b) Receiver Operating Characteristic (ROC) curve c) Precision-Recall curve d) Gradient descent
Answer: a) Confusion matrix, b) Receiver Operating Characteristic (ROC) curve, c) Precision-Recall curve
Which of the following are commonly used techniques for hyperparameter tuning in a machine learning model? (Select all that apply) a) Grid search b) Random search c) Bayesian optimization d) Gradient descent
Answer: a) Grid search, b) Random search, c) Bayesian optimization
Which of the following are commonly used algorithms for collaborative filtering in recommendation systems? (Select all that apply) a) User-based collaborative filtering b) Item-based collaborative filtering c) Singular Value Decomposition (SVD) d) Gradient descent
Answer: a) User-based collaborative filtering, b) Item-based collaborative filtering, c) Singular Value Decomposition (SVD)
Which of the following are commonly used techniques for data augmentation in computer vision? (Select all that apply) a) Image flipping b) Image rotation c) Image cropping d) Gradient descent
Answer: a) Image flipping, b) Image rotation, c) Image cropping
Which of the following are commonly used algorithms for anomaly detection in time series data? (Select all that apply) a) Autoregressive Integrated Moving Average (ARIMA) b) One-Class SVM c) Isolation Forest d) LSTM
Answer: b) One-Class SVM, c) Isolation Forest, d) LSTM
Which of the following are commonly used algorithms for clustering in machine learning? (Select all that apply) a) K-means clustering b) Hierarchical clustering c) Density-based clustering d) Gradient descent
Answer: a) K-means clustering, b) Hierarchical clustering, c) Density-based clustering
Which of the following are commonly used techniques for handling missing data in a dataset? (Select all that apply) a) Removing missing data b) Imputing missing data with mean/median/mode c) Imputing missing data with machine learning models d) Gradient descent
Answer: a) Removing missing data, b) Imputing missing data with mean/median/mode, c) Imputing missing data with machine learning models
Which of the following are commonly used activation functions in a neural network? (Select all that apply) a) Sigmoid function b) ReLU function c) Tanh function d) Logistic function
Answer: a) Sigmoid function, b) ReLU function, c) Tanh function
Which of the following are commonly used techniques for transfer learning in deep learning? (Select all that apply) a) Fine-tuning b) Feature extraction c) Pre-trained models d) Gradient descent
Answer: a) Fine-tuning, b) Feature extraction, c) Pre-trained models
Which of the following are commonly used techniques for dimensionality reduction in machine learning? (Select all that apply) a) Principal Component Analysis (PCA) b) Linear Discriminant Analysis (LDA) c) t-distributed Stochastic Neighbor Embedding (t-SNE) d) Gradient descent
Answer: a) Principal Component Analysis (PCA), b) Linear Discriminant Analysis (LDA), c) t-distributed Stochastic Neighbor Embedding (t-SNE)
Which of the following are commonly used techniques for sequence-to-sequence learning in natural language processing (NLP)? (Select all that apply) a) Recurrent Neural Networks (RNNs) b) Encoder-Decoder models c) Attention mechanism d) Gradient descent
Answer: a) Recurrent Neural Networks (RNNs), b) Encoder-Decoder models, c) Attention mechanism
Which of the following are commonly used algorithms for reinforcement learning in AI? (Select all that apply) a) Q-learning b) Deep Q-Network (DQN) c) Monte Carlo tree search (MCTS) d) Gradient descent
Answer: a) Q-learning, b) Deep Q-Network (DQN), c) Monte Carlo tree search (MCTS)
Which of the following are commonly used techniques for semi-supervised learning in machine learning? (Select all that apply) a) Self-training b) Co-training c) Generative adversarial networks (GANs) d) Gradient descent
Answer: a) Self-training, b) Co-training, c) Generative adversarial networks (GANs)
Which of the following are commonly used metrics for evaluating a classification model? (Select all that apply) a) Accuracy b) Precision c) Recall d) Mean squared error (MSE)
Answer: a) Accuracy, b) Precision, c) Recall
Which of the following are commonly used optimization algorithms in deep learning? (Select all that apply) a) Stochastic Gradient Descent (SGD) b) Adam optimizer c) Adagrad optimizer d) Gradient Boosting
Answer: a) Stochastic Gradient Descent (SGD), b) Adam optimizer, c) Adagrad optimizer
Which of the following are commonly used techniques for regularization in machine learning? (Select all that apply) a) L1 regularization b) L2 regularization c) Dropout d) Gradient boosting
Answer: a) L1 regularization, b) L2 regularization, c) Dropout
Which of the following are commonly used techniques for handling imbalance in a classification problem? (Select all that apply) a) Oversampling the minority class b) Undersampling the majority class c) SMOTE (Synthetic Minority Over-sampling Technique) d) Gradient descent
Answer: a) Oversampling the minority class, b) Undersampling the majority class, c) SMOTE (Synthetic Minority Over-sampling Technique)
Which of the following are commonly used loss functions in a neural network for a classification problem? (Select all that apply) a) Binary Cross-Entropy b) Categorical Cross-Entropy c) Mean Squared Error (MSE) d) Gradient descent
Answer: a) Binary Cross-Entropy, b) Categorical Cross-Entropy
Which of the following are commonly used models for time-series forecasting? (Select all that apply) a) ARIMA b) Prophet c) LSTM (Long Short-Term Memory) d) Gradient boosting
Answer: a) ARIMA, b) Prophet, c) LSTM (Long Short-Term Memory)
Which of the following are commonly used metrics for evaluating a regression model? (Select all that apply) a) Mean Absolute Error (MAE) b) Mean Squared Error (MSE) c) R-squared (R²) d) Gradient descent
Answer: a) Mean Absolute Error (MAE), b) Mean Squared Error (MSE), c) R-squared (R²)
Which of the following is NOT a common pre-processing technique used in Natural Language Processing (NLP)? a) Tokenization b) Stemming c) Dimensionality reduction d) Part-of-Speech (POS) tagging
Answer: c) Dimensionality reduction
Which of the following are commonly used clustering algorithms? (Select all that apply) a) K-means clustering b) Hierarchical clustering c) DBSCAN (Density-Based Spatial Clustering of Applications with Noise) d) Decision Trees
Answer: a) K-means clustering, b) Hierarchical clustering, c) DBSCAN (Density-Based Spatial Clustering of Applications with Noise)
Which of the following is NOT a common ensemble learning technique? a) Bagging b) Boosting c) Stacking d) Decision Trees
Answer: d) Decision Trees
Which of the following are commonly used hyperparameter tuning techniques in machine learning? (Select all that apply) a) Grid Search b) Random Search c) Bayesian Optimization d) Gradient descent
Answer: a) Grid Search, b) Random Search, c) Bayesian Optimization
Which of the following is NOT a common type of anomaly detection algorithm? a) Clustering-based anomaly detection b) Statistical-based anomaly detection c) Rule-based anomaly detection d) Gradient descent
Answer: d) Gradient descent
Learning often happens ONLINE for FREE and at your comfort zone. Enroll NOW.
Enjoy learning SWIFTLY.
For Homework/Academic Writing: homehubstudy@gmail.com
Quick Links
Resources
Registrations
Cookie Notice
We use cookies on our website to give you the most relevant experience by remembering your preferences and repeat visits. By clicking “Accept”, you consent to the use of ALL the cookies.
This website uses cookies to improve your experience while you navigate through the website. Out of these, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the website. We also use third-party cookies that help us analyze and understand how you use this website. These cookies will be stored in your browser only with your consent. You also have the option to opt-out of these cookies. But opting out of some of these cookies may affect your browsing experience.
Necessary cookies are absolutely essential for the website to function properly. These cookies ensure basic functionalities and security features of the website, anonymously.
Cookie
Duration
Description
cookielawinfo-checkbox-analytics
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Analytics".
cookielawinfo-checkbox-functional
11 months
The cookie is set by GDPR cookie consent to record the user consent for the cookies in the category "Functional".
cookielawinfo-checkbox-necessary
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Necessary".
cookielawinfo-checkbox-others
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Other.
cookielawinfo-checkbox-performance
11 months
This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Performance".
viewed_cookie_policy
11 months
The cookie is set by the GDPR Cookie Consent plugin and is used to store whether or not user has consented to the use of cookies. It does not store any personal data.
Functional cookies help to perform certain functionalities like sharing the content of the website on social media platforms, collect feedbacks, and other third-party features.
Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.
Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics the number of visitors, bounce rate, traffic source, etc.
Advertisement cookies are used to provide visitors with relevant ads and marketing campaigns. These cookies track visitors across websites and collect information to provide customized ads.
