Artificial intelligence is once again becoming the ultimate buzzword. After years of AI winters, the industry has embraced the concept of AI once again. With AI comes words like machine learning, big data, data science, supervised and unsupervised learning, neural network, etc.
It can be hard to keep track of the meaning of these buzzwords if you aren’t working with AI. Personally, it took me weeks to understand the different concepts and connections between the most common words. So, to make all of this easier for you, I have created this short AI dictionary to help you create an overview of the meaning of the most ‘modern’ AI words.
Artificial Inteligence (AI)
AI is the main word for describing working with creating intelligent machines or computer systems. AI attempts to build computer systems that think and act like humans.
The AI umbrella contains many different components and workflows, like machine learning and pattern recognition.
Big Data
As the name indicates, big data is a large amount of collected data. Big data is all types of data, as sales transactions from your point-of-sale system, data collected through Google analytic, registered phone calls in customer support, production machine data, customer key cards, and so on.
Computer Vision Systems
Is an AI technique there can view and extract information from real-world images. The purpose of computer vision systems is to understand and automate tasks that humans can do visually.
Computer vision enables computers and systems to discover information from digital images, videos, and other visual inputs — and based on that helps humans to take actions or make recommendations based on that information.
Data Science
Data science is an AI field there is using different methods, processes, algorithms, and systems to extract information, knowledge, and insight from a large set of various data – structured and unstructured. The purpose of data science is to translate the data into actionable insights.
Deep Learning
Is a subfield of machine learning. Deep learning uses neural networks to enabling systems and find clusters in data to make predictions with incredible accuracy. In Deep Learning, the neural network consists of a minimum of three layers, allowing the network to ‘learn’ to improve automation, performing analytical and physical tasks without human intervention.
Deep learning is the technology behind many machine learning applications and services, such as digital assistants, self-driving cars, and credit fraud detection.
Expert Systems
Expert systems take the knowledge from human experts and represent them as a set of rules there can be programmed so that the computer can assist humans in decision making.
Genetic Algorithms
A generic algorithm is a search-based algorithm used for solving optimization problems in machine learning. The algorithm is based on Darwin’s Theory of Evolution in nature: Survival of the fittest.
By simulating natural selection, reproduction and mutation, the genetic algorithm can produce high-quality solutions to various problems such as search and optimization.
Intelligent Agents
Intelligent agents is a software or entity that decides to enable artificial intelligence into action. It conducts operations in place of users or programs after sensing the environment.
The agent has some level of autonomy that allows it to perform specific, predictable, and repetitive tasks for users or applications. The two main functions of intelligent agents are perception and action.
Machine Learning
Is the most common AI technique. Machine learning is software there identifies patterns in massive databases. The system learns from data and identifies patterns in the various datasets with minimal human intervention.
Machine Vision
As the name indicates, machine vision is the ability for a computer to ‘see’.
The technology behind machine vision enables automatic inspection and analysis for applications including automated inspection, process control, and robotic guidance by using image processing.
Natural Language Processing
Is a machine learning algorithm that makes it possible for computers to understand and analyze natural human language.
Siri and Aleksa are good examples of how Natural Language Processing is working in real life.
Neural Network
Is the heart of the deep learning algorithm. Neural networks comprise sets of nodes distributed into an input layer, hidden layer, and output layer. Each node connects to another and has an associated weight and threshold.
If the output of the individual node is above the specified threshold value, the node is activated and sending a signal (data) to the next layer. Otherwise, the node isn’t forwarding the data.
The neural network is inspired by the human brain, mimicking how biological neurons send signals to one another.
Robotic Process Automation
Robotic Process Automation is when a machine can substitute for humans and computer systems for their control and information processing. Robotic process automation uses automation technologies to mimic back-office tasks for human workers, such as extracting data, filling forms, moving files, and sowing on.
Robotic process automation also covers the automation of f.x the household with robots as a robot vacuum cleaner or the robot automatizations in production.
Speech Recognition
Is the ability for a machine or program to identify words spoken aloud and convert them into readable text. Speech recognition uses different AI tools to understand unique inputs present in the recorded audio.
Supervised & Unsupervised Learning
Supervised Learning:
In supervised learning, are you feating your algorithm with labeled data. That means that some of the input data is already ‘tagged’ with the correct answer.
Unsupervised Learning:
Is the opposite of supervised learning. When working with unsupervised learning, you don’t supervise the algorithm with label data. Instead, you allow the algorithm to work on and identify the patterns without human interaction.
Structured & Unstructured Data
Structured Data:
Structured data is highly organized and formatted so that it is easily searchable.
Unstructured Data:
When working with unstructured data, the data is not predefined or organized, making it more challenging to collect, process, and analyze.
I will update the ‘dictionary’ sporadic in the future. If you want a word or concept explain don’t hesitate to contact me.
