Artificial Intelligence & Machine Learning Study Guide

Foundational vocabulary and concepts covering the hierarchy of AI, types of machine learning, analytics categories, and data quality terms.

Artificial Intelligence

The field of creating systems that can perform tasks that normally require human intelligence.

Machine Learning (ML)

A subset of AI where computers learn patterns from data rather than being explicitly programmed.

Supervised Learning

A type of machine learning where the model is given inputs (features) and correct outputs (labels) to learn the relationship between them.

Unsupervised Learning

A type of machine learning where the model receives only inputs and must discover patterns on its own without correct answers provided.

Reinforcement Learning

A process where an AI agent learns through trial and error by taking actions, receiving rewards or punishments, and adjusting its strategy.

Exploitation

In reinforcement learning, the strategy of using a path or action that has worked well before to achieve the highest reward.

Exploration

In reinforcement learning, the strategy of trying new actions to discover potentially better rewards than the current strategy.

Deep Learning

A subset of Machine Learning that uses Neural Networks with many layers.

Neural Networks

Algorithms inspired by the human brain that are used for tasks like image recognition, speech recognition, and Natural Language Processing (NLP).

Large Language Models (LLMs)

Deep Learning models trained on massive amounts of text, such as ChatGPT, Gemini, and Claude.

Generative AI

AI designed to create new content, such as text, images, music, or code.

Agentic AI

AI systems capable of planning and carrying out tasks with some autonomy, such as AI assistants or task automation agents.

Statistics

The mathematical foundation used to analyze and understand data.

Data Science

The field of using data, statistics, and computing to solve problems and gain insights.

Data Mining

The process of finding patterns and useful information in large datasets.

Optimization

The process of finding the best solution among many possibilities, such as best routes or model parameters.

Descriptive Analytics

A form of analytics that uses historical data to answer the question: "What happened?"

Predictive Analytics

A form of analytics that uses Machine Learning to answer the question: "What will happen?"

Prescriptive Analytics

A form of analytics that uses optimization techniques to answer the question: "What should we do?"

Bias

A data quality problem that occurs when some groups are underrepresented in the dataset (e.g., $90\%$ of data from one demographic).

Class Imbalance

A situation where one category in a dataset appears much more often than another category.

NaN

An abbreviation for "Not a Number," which is used to represent missing data in a dataset.

Sparse Data

Data that contains many missing values, such as a dataset that is $20\%$ missing.

Dense Data

Data where most values are present, such as a dataset that is $80\%$ dense.

Scatter Plot

A chart type used to show relationships between variables.

Histogram

A chart type used to show the distribution of data.