Introduction to AI and Machine Learning

These flashcards cover key concepts related to AI, machine learning types, model performance, and statistical methods.

Reactive AI

AI that responds to specific inputs with predetermined outputs and does not store or learn from past data.

Limited Memory AI

AI that stores and uses past data to learn from mistakes and improve performance over time.

Theory of Mind AI

A future stage of AI aimed at understanding human thought and emotion.

Superintelligent AI

AI that would be far more intelligent than the best human minds in every area; purely theoretical.

Narrow AI

Also known as weak AI, it performs well in one specific task but cannot perform anything outside of that task.

General AI

Also known as strong AI, it is theoretical AI that can act upon many different tasks just like a human.

Machine Learning (ML)

A type of AI that learns from data, creating rules based on output/input.

Deep Learning

A subfield of machine learning focusing on neural networks with many layers to enable complex tasks.

Supervised Learning

A type of machine learning that learns from labeled data, where each input is associated with an output.

Unsupervised Learning

A machine learning method where only the input is known and the goal is to find patterns in data without guidance.

Reinforcement Learning

An area of machine learning where an agent learns to make decisions by interacting with an environment.

Overfitted Model

A model that is too complex, memorizes training data well but performs poorly on new data.

Underfitted Model

A model that is too simple and fails to capture important relationships, performing poorly on all data.

Normalization (Min-Max Scaling)

Rescales features to a range between 0 and 1, improving model performance.

K-Nearest Neighbor (K-NN)

An instance-based algorithm that predicts new data labels based on the labels of the nearest neighbors.