Introduction to A.I.

Artificial Super Intelligence (ASI)

hypothetical future of AI system that would surpass human intelligence in ALL areas

Artificial General Intelligence (AGI)

the development of machines that possess the same broad, flexible, and adaptable intelligence of the human mind

Artificial Narrow Intelligence (ANI)

AI system designed to perform a specific task; most common form of AI today

ex. Siri, Alexa

Machine Learning

algorithms that learn from data to make predictions or decisions

Natural Language Processing (NLP)

enabling machines to understand, interpret, and generate human language for tasks like translation and chatbots

Types of ANI

• Machine learning

• Natural language processing (Google Translate)

• Robotics

• Knowledge representation and reasoning (Google Maps, GPS)

• Computer vision (Face ID, fingerprints)

• Planning and scheduling

Supervised Machine Learning

trains on labeled data to make predictions on new inputs; have an outcome to look out for

ex. image recognition, spam detection

Unsupervised Machine Learning

discovers patterns in unlabeled data for tasks like clustering and anomaly detection

Reinforcement Machine Learning

learns by interacting with an environment and receiving rewards/penalties; used in dynamic environments

ex. risk analyses for car insurance

Predicting Real Numbers

training a model to output a continuous value; makes precise numerical predictions

ex. predicting a stock price or a person’s height

Predicting Classifiers

trained to output a set of discrete categories

ex. classifying an email as “spam” or “not spam”

Cluster Analysis

grouping entities based on common attributes

Big Data

the explosion of digital data from a wide range of sources, such as social media, sensors, and the internet

Linear Models

simple, interpretable models that assume a linear relationship between the input features and the target variable

Ex. Linear regression and logistic regression

Non-linear Models

more complex models that can capture nonlinear patterns in the data

Ex. decision trees, random forests, deep neural networks

Neural Networks

composed of artificial neurons, each performing a simple computation; can be stacked like “legos” to compute more complex functions