A: AI is the field of computer science focused on creating systems that perform tasks requiring human-like intelligence, such as reasoning, learning, and problem-solving.
: ML is a subset of AI where systems learn from data to make predictions or decisions without explicit programming.
A: In traditional programming, rules and data are input to produce outputs. In ML, data and outputs are input to learn the rules.
A: Supervised learning is an ML approach where models are trained on labeled data with input-output pairs to predict outcomes.
A:
Unsupervised learning involves finding patterns in unlabeled data without predefined outputs, e.g., clustering or dimensionality reduction.
A: Reinforcement learning is an ML paradig
A: Reinforcement learning is an ML paradigm where an agent learns by interacting with an environment, receiving rewards or penalties.
A: A feature is a measurable property or characteristic of the data used as input for an ML model.
A: A label is the output variable or target that the model aims to predict in supervised learning.
A: A dataset is a collection of data points used to train, validate, or test an ML model.
A: Examples include spam email filtering, image recognition, recommendation systems, and predictive maintenance.
A: A training set is the portion of a dataset used to train an ML model
A: A test set is a separate portion of a dataset used to evaluate a model’s performance after training.
A: A validation set is used during training to tune model hyperparameters and prevent overfitting.
A: Generalization is a model’s ability to perform well on unseen data.
A: A model is a mathematical representation learned from data to make predictions or decisions.