People often assume artificial intelligence means robots coming to life to interact with humans. However, this notion misconstrues the meaning of AI.
Artificial intelligence is highly multifaceted with subcomponents that extend far beyond the “robot-human relationship” misconception.
Artificial intelligence terms A to Z:
- AI terms A through E
- AI terms F through J
- AI terms K through O
- AI terms P through T
- AI terms U through Z
Relevant artificial intelligence terminology
While browsing the internet, you've probably heard terms like "data mining" and "machine learning," but never could find a concise definition to help you understand what you were reading. Now? You don't have to look far. Below are brief definitions of words and phrases related to AI.
Note: not all letters of the alphabet are listed if they do not contain relevant enough terms.
AGI, ANI, ANN, CNN...what do they all mean?
Algorithm: a formula given to a computer in order for it to complete a task (i.e. a set of rules for a computer)
Artificial intelligence: a subset of computer science that deals with computer systems performing tasks with similar, equal, or superior intelligence to that of a human (e.g. decision-making, object classification and detection, speech recognition and translation)
Artificial general intelligence (AGI): also known as strong AI, AGI is a type of artificial intelligence that is considered human-like, and still in its preliminary stages (more of a hypothetical existence in present day)
Artificial narrow intelligence (ANI): also known as weak AI, ANI is a type of artificial intelligence that can only focus on one task or problem at a given time (e.g. playing a game against a human competitor). This is the current existing form of AI.
Artificial neural network (ANN): a network modeled after the human brain by creating an artificial neural system via a pattern-recognizing computer algorithm that learns from, interprets, and classifies sensory data
Backpropagation: shorthand for “backward propagation of errors,” is a method of training neural networks where the system’s initial output is compared to the desired output, then adjusted until the difference (between outputs) becomes minimal
Bayesian networks: also known as Bayes network, Bayes model, belief network, and decision network, is a graph-based model representing a set of variables and their dependencies
Big data: large amounts of structured and unstructured data that is too complex to be handled by standard data-processing software
Chatbots: a chat robot that can converse with a human user through text or voice commands. Utilized by e-commerce, education, health, and business industries for ease of communication and to answer user questions.
Image courtesy of IBM
Classification: algorithm technique that allows machines to assign categories to data points
Clustering: algorithm technique that allows machines to group similar data into larger data categories
Cognitive computing: computerized model that mimics human thought processes by data mining, NLP, and pattern recognition
Computer vision: when a machine processes visual input from image files (JPEGs) or camera feeds
Convolutional neural network (CNN): a type of neural network specifically created for analyzing, classifying, and clustering visual imagery by using multilayer perceptrons
Data mining: the process of sorting through large sets of data in order to identify recurring patterns while establishing problem-solving relationships
Deep learning: a machine learning technique that teaches computers how to learn by rote (i.e. machines mimic learning as a human mind would, by using classification techniques)
This section should be of particular interest if you enjoy experimental AI!
Generative adversarial networks (GAN): a type of neural network that can generate seemingly authentic photographs on a superficial scale to human eyes. GAN-generated images take elements of photographic data and shape them into realistic-looking images of people, animals, and places.
GIF courtesy of Medium.com
Genetic algorithm: an algorithm based on principles of genetics that is used to efficiently and quickly find solutions to difficult problems
Heuristic: a computer science technique designed for quick, optimal, solution-based problem solving
Image recognition: the process of identifying or detecting an object or feature of an object in an image or video
Some of the most used terms lie between K-O in the AI glossary!
Limited memory: systems with short-term memory limited to a given timeframe
Machine learning (ML): focuses on developing programs that access and use data on their own, leading machines to learn for themselves and improve from learned experiences
Machine translation: an application of NLP used for language translation (human-to-human) in text- and speech-based conversations
Natural language processing (NLP): helps computers process, interpret, and analyze human language and its characteristics by using natural language data
Neural networks: see artificial neural networks
Optical Character Recognition (OCR): conversion of images of text (typed, handwritten, or printed) either electronically or mechanically, into machine-encoded text
Robots, robots, robots. You'll finally find some robot-centric definitions here!
Pattern recognition: automated recognition of patterns found in data
Reactive machines: can analyze, perceive, and make predictions about experiences, but do not store data; they react to situations and act based on the given moment
Recurrent neural network (RNN): a type of neural network that makes sense of and creates outputs based on sequential information and pattern recognition
Reinforcement learning: a machine learning method where the reinforcement algorithm learns by interacting with its environment, and is then penalized or rewarded based off of decisions it makes
Robotics: focused on the design and manufacturing of robots that exhibit and/or replicate human intelligence and actions
Robotic process automation (RPA): uses software with AI and ML capabilities to perform repetitive tasks once completed by humans
Strong AI: see artificial general intelligence (AGI)
Structured data: clearly defined data with easily searchable patterns
Supervised learning: a type of machine learning where output datasets teach machines to generate desired outcomes or algorithms (akin to a teacher-student relationship)
Transfer learning: a system that uses previously-learned data and applies it to a new set of tasks
Turing Test: a test created by computer scientist Alan Turing (1950) to see if machines could exhibit intelligence equal to or indistinguishable from that of a human
Fewer AI terms fall between U-Z, but the most important ones are here on display.
Unstructured data: data without easily searchable patterns (e.g. audio, video, social media content)
Unsupervised learning: a type of machine learning where an algorithm is trained with information that is neither classified nor labeled, thus allowing the algorithm to act without guidance (or supervision)
Weak AI: see artificial narrow intelligence (ANI)
On the road to expertise
With these frequently-researched terms fresh in your mind, you’re ready to tackle AI head-on and continue your knowledge exploration adventure!