Introduction to Machine Learning and Artificial Intelligence 301
Introduction to Machine Learning and Artificial Intelligence covers advances in the field of artificial intelligence (AI) enabled by machine learning. Machine learning uses complex algorithms that enable computing devices to learn from input data and produce outputs without traditional programming. Basic types of machine learning include supervised machine learning, unsupervised machine learning, and reinforcement machine learning.
Machine learning AI has a growing range of potential uses in various industries, including manufacturing. Manufacturers transitioning to Industry 4.0 should develop a basic understanding of how machine learning applications can benefit a variety of manufacturing processes. After taking this course, users will understand how data is used in algorithms that enable the three types of machine learning and gain insight into how machine learning AI capabilities may benefit their own manufacturing tasks and operations.
Number of Lessons 13
- Introduction to Machine Learning and Artificial Intelligence
- The Machine Learning Process
- Machine Learning Capabilities
- Supervised Versus Unsupervised Machine Learning
- Reinforcement Machine Learning
- Machine Learning Review
- Regression Algorithms
- Classification Algorithms
- Clustering Algorithms
- Neural Networks
- Deep Learning
- Final Review
- Applications of Machine Learning and AI in Manufacturing
- Describe early developments in machine learning and artificial intelligence.
- Describe the machine learning process.
- Distinguish between basic AI programming and machine learning AI.
- Distinguish between supervised and unsupervised machine learning.
- Describe reinforcement machine learning.
- Describe basic regression algorithms.
- Describe basic classification algorithms.
- Describe basic clustering algorithms.
- Describe neural networks and their uses.
- Describe how neural networks enable deep learning.
- Identify applications for machine learning AI in manufacturing.
Steps taken by an agent in a reinforcement learning environment to achieve a goal. Actions taken by an AI in reinforcement machine learning change the state of the simulated environment, which affects future actions.
A logical rule that determines how nodes in a neural network calculate inputs and produce outputs. Activation functions determine a neural network's level of complexity.
AM. The process of joining or solidifying materials to make an object based on a three-dimensional computer model. Additive manufacturing methods typically build up layers of material to create an object.
The entity in a reinforcement learning environment that performs actions. The agent in reinforcement machine learning is the artificial intelligence seeking to learn the correct actions to achieve a goal.
artificial intelligence. The ability of a machine or computer to imitate intelligent human behavior. AI allows machines to perform a process with autonomy.
A logical or mathematical process designed to systematically solve a problem. Algorithms are coded into software to form the rules by which artificial intelligence functions.
An irregularity in a data set that does not fit with general trends or patterns in the data. Anomalies in a data set could indicate erroneous data or outliers that can be studied to learn new information.
AI. The ability of a machine or computer to imitate intelligent human behavior. Artificial intelligence allows machines to perform a process with autonomy.
artificial neural networks
A web of connected nodes designed to resemble the structure and function of neurons in the human brain. Artificial neural networks have been key to building advanced machine learning models for artificial intelligence (AI).
A conceptual model for artificial intelligence designed to resemble the basic structure and function of a neuron in the human brain. Artificial neurons stemmed from the idea that a computing device could process information similar to a human.
The process of analyzing a data set to discover unknown relationships between items in the data. Association algorithms are effective for analyzing unlabeled data in unsupervised machine learning.
best fit line
A straight line on a regression chart that cuts through all plotted data points most accurately. The best fit line is drawn using input and output variables from the training set of data and is used to predict the output variable of the validation set of data.
The process of analyzing and dividing inputs from a data set into two groups based on specified conditions that are either true or false. Binary classification is often the goal of supervised machine learning.
An algorithm that separates data into two categories using either a 1 or a 0 to define each group. Binary classifiers can be used to simplify more complex data into binary categories.
The smallest unit of information on a computing device. Binary digits are either 1s or 0s.
A dynamic in which one variable is directly affected by another. Causal relationships between variables can be depicted on a regression chart.
A set of steps used to analyze or predict whether or not a data output falls in a specified category. Classification algorithms can be used in supervised machine learning models.
A combination of hardware and software computing technology typically provided by a third party that allows clients to access, store, and process data remotely through an internet connection. Cloud-based servers can provide multiple clients with access to unlimited storage and processing capabilities but may pose greater cybersecurity risks than secure local area network servers (LANs).
The processes of analyzing a data set to discover similar patterns, then dividing the data into groups based on these patterns. Clustering algorithms for unsupervised machine learning allow an artificial intelligence (AI) to analyze large, unlabeled data sets.
A set of steps or calculations used to analyze an unlabeled data set in order create groups within the data based on similarities. Clustering algorithms can be used by artificial intelligence (AI) in unsupervised machine learning to discover unknown information about the data.
Digital instructions written in a computer programming language that a computing device can translate into readable data. Computer coding uses different combinations of letters, numbers, and symbols, which a computer interprets and presents as a program, website, or other application.
A person who codes digital commands into a computing device. Computer programmers use various computer programming languages that tell a device what actions to perform.
A deep learning capability that enables an artificial intelligence (AI) to detect and identify objects by recognizing visual patterns through a camera or on a screen. Computer vision can be useful for supervised or unsupervised machine learning but requires very large amounts of visual data.
CAD. A method of designing two- and three-dimensional objects using computers and software. Computer-aided design is most often used to create part models for production.
Input or output data that can be any numerical value. Continuous variables are more specific than other types of variables.
An effort to disrupt, disable, or gain illegal access to a digital device or network. Cyber attacks include hacking, phishing, and installing malware.
Any potential event or attack that could access or damage computers or digital networks. Cyber threats may include inadvertent events or malicious attacks from hackers.
CPS. One or more hardware devices that link physical components and processes with interconnected digital components and processes. Cyber-physical systems are used in Industry 4.0 to monitor and control physical components using digitally automated technology.
Protection against criminal or unauthorized access to computer networks, programs, and data. Cybersecurity has become a major industrial concern as networking and connectivity have increased.
The process of analyzing data with software in order to draw out unknown patterns in the data. Data mining is used to discover useful information in large sets of unlabeled, unorganized data.
Similarities or trends discovered among items within a data set. Data patterns are key to enabling machine learning for artificial intelligence (AI).
An individual who uses computing systems to perform data analysis in order to interpret and present insights gained from data. Data scientists can help manufacturers operate more efficiently by adjusting processes based on data analysis.
A binary classification method in which data is divided based on whether conditions for the data are either true or false. Decision trees can convert continuous variables into binary outputs.
An advanced form of machine learning that uses neural networks with multiple hidden layers. Deep learning algorithms can enable machines to exhibit advanced, human-like behaviors but require significant amounts of data.
The output data in a regression algorithm that may be impacted by various input variables. The dependent variable changes in response to the independent variable.
Consisting of information that is input or output electronically as a series of pulses or signals, often resulting in binary strings of 0s and 1s. Digital computing devices interpret various programming commands as binary digits.
A virtual representation of a physical asset or part. A digital twin evolves with the asset throughout its product lifecycle.
The period of time when a machine or system is not operating and is not producing or performing work. Downtime due to unscheduled service or maintenance can have a negative impact on overall production efficiency.
energy demand forecasting
The process of analyzing historical data on energy usage to uncover trends used to optimize future usage. Energy demand forecasting can be enhanced by deep learning models that can potentially manage energy usage efficiency autonomously.
The middle row or rows of nodes in an artificial network that perform specified processes and calculations on the data stored in the input layer. Hidden layer nodes typically contain different weights and thresholds that affect each node's calculated result of the inputs.
Previously recorded data for which all data outputs are known. Historical data can be used to train machine learning models to predict outputs in unknown data sets.
A conditional command that executes when a particular portion of a program is met, and executes an alternate instruction if the same condition is not met. If-Then commands are commonly used in computer programs.
Industrial Internet of Things. A network of physical devices used in manufacturing that contain computing systems that allow them to send and receive data. The IIoT allows devices to exchange data and automate processes without any human intervention.
The input data in a regression algorithm that may influence the output, or end result. The independent variable causes the dependent variable to change.
A stage in manufacturing that uses connected devices and digital technologies. Industry 4.0 uses automation and data exchange to achieve advancements in a variety of industries.
Information given to a computing device in order to be processed or analyzed. Input data is used by machine learning algorithms in order to produce an output.
The first row of nodes in an artificial neural network that store the collected data to be analyzed by the machine learning algorithm. The input layer can contain one or several input nodes.
Intrusion Detection and Prevention Systems
IDPS. A hardware or software tool that can monitor activity on digital systems to detect cyber threats and take actions to prevent them. Intrusion Detection and Prevention Systems that utilize machine learning AI can help identify and prevent unknown threats.
Repeated constantly. Iterative, complex logical processes or mathematical calculations that might be too long or difficult for humans can often be completed quickly by computing technology.
A set of digital information that is defined prior to being analyzed by a computer. Labelled data is required in supervised machine learning algorithms.
A statistical analysis process that models the relationship between one input or independent variable and one output or dependent variable, to examine the correlation between them. Linear regression can be used in supervised machine learning to help an artificial intelligence (AI) predict outputs based on a single input.
linear regression chart
A chart or graph that depicts data points and a best fit line produced by a linear regression algorithm. Linear regression charts help data scientists visualize the cause-effect relationship between a dependent variable and an independent variable.
local area network servers
LAN servers. A computer or program that manages networking functions for a variety of devices within a single geographical location. Local area network servers store, process, and transfer information between other devices connected to the local network.
The area of business that focuses on the purchase, production, transport, and distribution of materials within a company. Logistics planning and management efficiency can be improved with machine learning algorithms.
The process that enables a digital system to analyze data in order to build predictive models and make decisions autonomously. Machine learning is a key benefit of Industry 4.0.
machine learning model
A computing function that uses one or more algorithms to perform specific calculations on data to produce an output. Machine learning models may use supervised, unsupervised, or reinforcement learning methods.
Manufacturing a part by using a tool to remove material in the form of chips. Milling, drilling, turning, sawing, and grinding are all various forms of machining operations.
natural language processing
NLP. A deep learning capability that enables an artificial intelligence (AI) to detect and identify language patterns audio speech or written text. Natural language processing requires very large amounts of data.
A single unit in an artificial neural network that receives an input and produces an output. Nodes in a neural network can store information or perform a variety of actions.
A calculated result or action produced by a computing device after processing data inputs. Outputs produced by computing devices may be in the form of data or may include a response to data.
The last row of nodes in an artificial neural network where the final processed result is produced. The output layer may contain one or more nodes depending on the algorithm's complexity.
A calculated result or action produced by a computing device after processing data inputs. Outputs produced by computing devices may be in the form of data or may include a response to data.
Expenses associated with operating buildings and equipment, including rent, insurance, utilities, and repairs. Overhead costs can potentially be reduced by machine learning algorithms trained to optimize energy usage.
Anything that is presented after the occurrence of a behavior to increase the likelihood of that behavior occurring again. Positive reinforcement is used in reinforcement learning to increase the chances of correct outputs.
Expenses directly related to starting or running a manufacturing operation. Production costs include any expenses associated with purchasing necessary machines, materials, and labor.
QA. A system of proactively managing quality by regulating the quality of materials, assembly processes, products, and components. Quality assurance practices such as inspection can be improved by automation enabled by machine learning.
A product development technique where additive manufacturing processes are used to create prototypes for a traditional manufacturing operation. Rapid prototyping allows engineers to quickly create a number of prototypes in a short time period, reducing lead time.
A set of steps and calculations used to analyze or predict how input or independent variables impact an output or dependent variable. Regression algorithms can be used in supervised machine learning models.
reinforcement machine learning
A process in which an artificial intelligence (AI) learns the best actions to achieve a goal through trial and error. Reinforcement machine learning enables an AI to learn details about inputs and produce correct outputs autonomously.
A process that captures geometric data of an existing object to convert it to a 3D computer-aided design (CAD) model. Reverse engineering can be used to create an additive manufacturing part from a traditionally manufactured part.
An instance of positive reinforcement given to an agent for carrying out a correct action in reinforcement learning. Rewards are used to train an artificial intelligence (AI) to produce correct actions in a simulated environment.
A practice setting designed to mimic or resemble the environment in a real-life situation. Simulated environments can be physical or virtual environments.
An algorithm first proposed by Frank Rosenblatt designed to resemble the function of a human neuron. A basic single-layer perceptron receives an input and produces a simple true or false output.
Capable of sending and receiving data without human intervention. Smart technology generally requires internet connectivity to enable data processing.
The ability of an artificial intelligence (AI) to interpret audible speech by identifying speech patterns. Speech recognition technology requires complex machine learning algorithms.
The current status of a simulated learning environment that defines available actions. State changes in the environment can also change what actions are available.
An activation function that assigns threshold values to nodes in a neural network. A step function causes each node to produce a binary output.
The total amount resulting from adding two or more numbers together. The sum of weighted values calculated by a node in a neural network must be above the node's assigned threshold value in order for the node to activate.
supervised machine learning
A process in which a human operator labels data inputs for a machine learning model and defines the desired outputs the model should produce. Supervised machine learning typically requires extensive human labor in order to prepare and label data sets.
A marketing tactic that tailors different marketing messages to different customers based on purchasing habits or other information. Target marketing can be greatly enhanced using machine learning algorithms to analyze customer data.
A known output value in the test data set that a machine learning model is designed to produce after calculating the test data inputs. Machine learning models that produce outputs close to the target result are considered effective models.
A group of data for which the output variable is not known. A test data set is used to test the accuracy of a regression algorithm.
A numerical limit, typically between zero and one, that is set for each node in the hidden layers of a neural network. The threshold value activates a node if that node calculates a weighted sum that is above the threshold.
Previously recorded data used to train and improve machine learning algorithms. The training data for supervised learning includes historical data for both inputs and outputs.
A test designed by Alan Turing that could theoretically be used to rate the intelligence of a computer. The Turing Test essentially rated a computer's responses to text-based questions on whether the computer's response could be differentiated from a human's.
A set of digital information that is not defined prior to being analyzed by a computer. Unlabeled data can be analyzed using unsupervised machine learning algorithms.
unsupervised machine learning
A process in which a machine learning model processes and analyzes unlabeled data and produces outputs without human interaction. Unsupervised machine learning models help discover patterns in data that humans may not recognize.
A group of data for which the output variable is not known. A validation set is used to test the accuracy of a regression algorithm.
A specific numerical value assigned to a vector connecting the output of one node in a neural network to the input of another node on the next layer. Weights allow neural networks to assign different levels of importance to different inputs.
A node's output value multiplied by it's assigned weight. Weighted values are used as input values for connected nodes on the next layer.