Artificial Intelligence Basics

Natural language understanding

As a subset of NLP, NLU deals with helping machines recognize the intended meaning of language - taking into account its subtle nuances and any grammatical errors.

Bias

Assumptions made by a model that simplify the process of learning how to do its assigned task. Most ML models perform better with low bias, as these assumptions can negatively affect results.

Predictive analytics

By combining data mining and machine learning, this type of analytics is built to forecast what will happen within a given timeframe based on historical data and trends.

Autonomous

Can perform its task or tasks without needing human intervention.

Bounding box

Commonly used in image or video tagging, this is an imagery box drawn on visual information. The contents of the box are labeled to help a model recognize it as a distinct type of object.

Intent

Commonly used in training data for chatbots and other natural language processing tasks, this is a type of label that defines the purpose or goal of what is said. For example, the intent for the phrase "turn the volume down" could be "decrease volume".

Hyperparameter

Occasionally used interchangeably with parameter, although the terms have some subtle differences. Values that affect the way your model learns, set manually outside the model.

Transfer learning

Spending time teaching a machine to do a related task, then allowing it to return to its original work with improved accuracy. Ex: taking a model that analyzes sentiment in product reviews and asking it to analyze tweets for a week.

Machine learning

Subset of AI particularly focused on developing algorithms that will help machines to learn and change in response to new data, without the help of a human being.

Linguistic annotation

Tagging a dataset of sentences with the subject of each sentence, ready for some form of analysis or assessment. Common uses for linguistically annotated data include sentiment analysis and NLP.

Semantic annotation

Tagging different search queries or products with the goal of improving the relevance of a search engine

Turing test

Tests chi

Pattern recognition

The distinction between pattern recognition and machine learning is often blurry, but this field is basically concerned with finding trends and patterns in data.

Artificial Intelligence

The general concept of machines acting in a way that simulates or mimics human intelligence. Can have a variety of features, such as human-like communication or decision making.

Data mining

The process of analyzing datasets in order to discover new patterns that might improve the model

Sentiment analysis

The process of identifying and categorizing opinions in a piece of text, often with the goal of determining the writer's attitude towards something.

Entity annotation

The process of labeling unstructured sentences with information so that a machine can read them. Example: labeling all people, organizations and location in a document

Machine translation

The translation of text by an algorithm, independent of human involvement

Supervised learning

The type of machine learning where structured datasets, with inputs and labels, are used to train and develop an algorithm

Natural language processing

The umbrella term for any machine's ability to perform conversational tasks, like recognizing what is said to it, understanding the intended meaning and responding intelligibly.

Test data

The unlabeled data used to check that a machine learning model is able to perform its assigned task

Neural network

Also called a neural net, a neural network is a computer system designed to function like the human brand. It can perform many tasks involving speech, vision and board game strategy.

Machine intelligence

An umbrella term for various types of learning algorithms, including ML and DL.

Entity extraction

An umbrella term referring to the process of adding structure to data so that a machine can read them. May be done by humans or by an ML model.

Model

A broad term referring to the product of AI training, created by running an ML algorithm on training data

Dataset

A collection of related data points, usually with a uniform order and tags

Computational learning theory

A field within AI primarily concerned with creating and analytics ML algorithms

Deep learning

A function of AI that imitates the human brain by learning from the way data is structured, rather than from an algorithm that's programmed to do one specific thing

Corpus

A large dataset of written or spoken material that can be used to train a machine to perform linguistic tasks

Forward chaining

A method in which.a machine must work from a problem to find a potential solution. By analyzing a range of hypotheses, the AI must determine those that are relevant to the problem.

Reinforcement learning

A method of teaching AI that sets a goal without specific metrics, encouraging the mode to test different scenarios rather than find a specific answer. Based on human feedback, the model can manipulate the next scenario to get better results.

Backward Chaining

A method where the model starts with the desired output and works in reverse to find data that might support it.

Label

A part of training data that identifies the desired output for that particular piece of data

Python

A popular programming language that can run on several OS platforms.

Chatbot

A program designed to communication with people through text or voice commands in a way that mimics human-to-human conversation.

Algorithm

A set of rules that a machine can follow to learn how to do a task

Overfitting

A symptom of machine learning training in which an algorithm is only able to work on or identify specific examples present in the training data. A working model should be able to use the general trends behind the data to work on new examples.

Parameter

A variable inside the model that helps it to make predictions. Its value can be estimated using data and they are usually not set by the person running the model.

General AI

AI that could successfully do any intellectual task that can be done by any human being. Also referred to as strong AI.

Strong AI

Ai that is equal to the human mind when it comes to ability. Also known as general AI.

Training data

All of the data used during the process of training a machine learning algorithm.

Big data

Datasets that are too large or complex to be used by traditional data processing applications

Data science

Drawing from statistics, computer science and information science, this interdisciplinary field aims to use a variety of scientific methods, processes and systems to solve problems involving data.

Cognitive computing

Effectively another way to say AI. It's used by marketing teams to avoid the science fiction aura that sometimes surrounds AI.

Natural language generation

Information is transformed into content, enabling such functions as text-to speech, automation of reports and the production of content for awe or mobile applications.