ML-Deep learning Introduction

Deep learning is a subfield of machine learning that focuses on algorithms inspired by the structure and function of:

• Human brain

• Classical mechanics

• Quantum physics

• Genetic algorithms

Which of the following is a fundamental building block in a deep learning model?

• Decision tree

• Naive Bayes classifier

• Perceptron

• k-Nearest Neighbors (k-NN)

What is the primary advantage of using deep learning models over traditional machine learning models?

• Better interpretability

• Faster training time

• Ability to handle high-dimensional data

• Smaller computational requirements

What type of neural network layer is responsible for learning hierarchical features from the input data?

• Activation layer

• Dense layer

• Convolutional layer

• Pooling layer

Which deep learning architecture is commonly used for sequential data processing, such as natural language processing and speech recognition?

• Convolutional Neural Network (CNN)

• Recurrent Neural Network (RNN)

• Transformer

• Generative Adversarial Network (GAN)

The process of adjusting the weights and biases in a neural network to minimize the error during training is known as:

• Backpropagation

• Gradient descent

• Stochastic optimization

• Reinforcement learning

What is the "ReLU" activation function commonly used in deep learning?

• Rectified Linear Unit

• Logistic sigmoid

• Hyperbolic tangent

• Softmax

What is the purpose of the "dropout" regularization technique in deep learning?

• To reduce overfitting by randomly deactivating neurons during training

• To increase the model capacity by adding more layers

• To speed up the training process by reducing the number of iterations

• To improve convergence by adjusting the learning rate dynamically

In deep learning, what is the purpose of the "loss function"?

• To control the learning rate during training

• To initialize the weights and biases of the model

• To measure the model's performance and guide weight updates

• To optimize the hyperparameters of the neural network

Which of the following optimization algorithms is commonly used to train deep learning models?

• k-Means

• K-Nearest Neighbors (k-NN)

• Gradient Boosting

• Stochastic Gradient Descent (SGD)