AI Basics: Machine Learning

What is machine learning?

• Machine learning is a type of coffee maker

• Machine learning is a type of bicycle

• Machine learning is a type of sandwich

• Machine learning is a subset of artificial intelligence that involves the development of algorithms and statistical models to perform a specific task without explicit instructions, relying on patterns and inference instead.

What are the two main types of machine learning?

• supervised learning and unsupervised learning

• deep learning

• semi-supervised learning

• reinforcement learning

Explain the difference between supervised and unsupervised learning.

• In supervised learning, the model is trained on unlabeled data, while in unsupervised learning, the model is trained on labeled data.

• Supervised learning uses neural networks, while unsupervised learning uses decision trees.

• Supervised learning is used for classification tasks only, while unsupervised learning is used for regression tasks only.

• In supervised learning, the model is trained on labeled data, while in unsupervised learning, the model is trained on unlabeled data.

What is the role of labeled data in supervised learning?

• Labeled data is not necessary in supervised learning

• Labeled data only confuses the model in supervised learning

• Labeled data helps the model learn the mapping between input features and the corresponding output labels.

• Labeled data is used for unsupervised learning, not supervised learning

Give an example of a real-world application of machine learning.

• Online shopping carts

• Recommendation systems

• Weather forecasting

• Facial recognition technology

What is overfitting in machine learning?

• Overfitting is when a model learns the details and noise in the training data to the extent that it negatively impacts the model's performance on new data.

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

• Overfitting is when a model learns only the general patterns in the training data.

• Overfitting is beneficial as it ensures the model performs well on new data.

How can overfitting be prevented?

• Increasing model complexity

• Ignoring validation data

• Using the same dataset for training and testing

• Using techniques such as cross-validation, regularization, early stopping, and reducing model complexity.

What is a neural network?

• A neural network is a type of computer hardware used for data storage.

• A neural network is a series of algorithms that endeavors to recognize underlying relationships in a set of data through a process that mimics the way the human brain operates.

• A neural network is a type of plant species found in tropical regions.

• A neural network is a type of weather phenomenon that occurs in the stratosphere.

What is the purpose of activation functions in neural networks?

• To slow down the learning process

• To introduce non-linearity and enable the neural network to learn complex patterns.

• To decrease the complexity of the neural network

• To remove non-linearity from the neural network

What is backpropagation in the context of neural networks?

• Backpropagation is a process of selecting the activation function for each neuron in a neural network.

• Backpropagation is a method used to increase the number of layers in a neural network.

• Backpropagation is a method used to train neural networks by calculating the gradient of the loss function with respect to the weights of the network.

• Backpropagation is a technique to randomly initialize the weights of a neural network.