RemoDesk AI/ML Internship Test

What is supervised learning?

• Unsupervised learning uses labeled data to train models.

• Supervised learning is a machine learning approach that uses labeled data to train models.

• Supervised learning is a type of reinforcement learning.

• Supervised learning is a method that requires no data for training.

Define unsupervised learning.

• Unsupervised learning is a method for supervised classification tasks.

• Unsupervised learning only works with structured data.

• Unsupervised learning is a machine learning approach that finds patterns in data without labeled outcomes.

• Unsupervised learning requires labeled data to train models.

What is overfitting in machine learning?

• Overfitting occurs when a model is too simple and cannot capture the underlying patterns in the data.

• Overfitting is when a model performs poorly on both training and unseen data due to lack of data.

• Overfitting is when a model performs well on training data but poorly on unseen data due to excessive complexity.

• Overfitting refers to a model that generalizes well to new data but fails on training data.

Explain the difference between classification and regression.

• Both classification and regression predict discrete outcomes.

• Classification is used for time series analysis, while regression is for image recognition.

• Classification predicts numerical values, while regression predicts categories.

• Classification predicts categories, while regression predicts continuous values.

What is a confusion matrix?

• A confusion matrix is a type of neural network architecture.

• A confusion matrix is a statistical test for hypothesis testing.

• A confusion matrix is a method for data normalization.

• A confusion matrix is a table that summarizes the performance of a classification model by comparing actual and predicted classifications.

What is the purpose of cross-validation?

• To reduce the size of the dataset used for training.

• To evaluate the performance and generalization ability of a model.

• To increase the training speed of a model.

• To eliminate the need for model tuning.

What is a neural network?

• A neural network is a computational model that simulates the way human brains process information, consisting of interconnected layers of nodes.

• A neural network is a type of hardware used for gaming.

• A neural network is a biological structure found in plants.

• A neural network is a social network for connecting people.

Describe the architecture of a simple feedforward neural network.

• A simple feedforward neural network has an input layer, hidden layers, and an output layer, with fully connected neurons.

• A simple feedforward neural network uses recurrent connections between layers.

• A simple feedforward neural network has a single layer of neurons with no connections.

• A simple feedforward neural network consists of only an input layer and an output layer.

What is the role of activation functions in neural networks?

• Activation functions help in reducing the size of the dataset.

• Activation functions are responsible for initializing the weights of the network.

• Activation functions are used to increase the number of layers in a network.

• Activation functions enable neural networks to learn non-linear mappings.

Explain the concept of backpropagation.

• Backpropagation is a technique for visualizing neural network architectures.

• Backpropagation is a method for training neural networks by propagating errors backward through the network to update weights.

• Backpropagation is a method for generating random weights in neural networks.

• Backpropagation is a process of collecting data from the output layer only.