Deep Learning Fundamentals

What is deep learning primarily used for?

• Basic arithmetic calculations

• Data storage and management

• Web development and design

• Deep learning is primarily used for image and speech recognition, natural language processing, and autonomous systems.

Which of the following is a common framework for deep learning?

• Keras

• Pandas

• TensorFlow

• Scikit-learn

What is the main building block of a neural network?

• Activation function

• Neuron

• Layer

• Node

What does the term 'activation function' refer to?

• A technique for feature extraction.

• A method for data normalization.

• A type of neural network architecture.

• A mathematical function that determines the output of a neuron in a neural network.

Which of the following is NOT a type of neural network?

• Linear Regression

• Generative Adversarial Network

• Recurrent Network

• Convolutional Network

What is overfitting in the context of deep learning?

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

• Overfitting refers to the process of reducing the complexity of a model to improve generalization.

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

• Overfitting is when a model performs equally well on both training and unseen data.

What is the purpose of a loss function?

• The purpose of a loss function is to measure the error of a model's predictions.

• To determine the model's training duration.

• To increase the model's complexity.

• To optimize the model's architecture.

Which optimization algorithm is commonly used in deep learning?

• Batch Gradient Descent

• Newton's Method

• Stochastic Gradient Descent (SGD)

• Simulated Annealing

What does 'backpropagation' do in a neural network?

• Backpropagation updates the weights of a neural network to minimize the error in predictions.

• Backpropagation generates new training data for the network.

• Backpropagation increases the error in predictions.

• Backpropagation is used to initialize the neural network.

What is a convolutional neural network (CNN) primarily used for?

• Natural language processing

• Reinforcement learning

• Image and video recognition

• Time series forecasting